Add MCP provider support to bring-your-own-connector#623
Conversation
Introduce MCP connectors as a second type of custom provider alongside REST API providers. Add MCP JSON payload examples for all 4 auth types (OAuth, Bearer, Basic, API Key), document list_scoped_tools and execute_tool for MCP tool calling, and update framing across all pages to cover both REST and MCP modes.
AkshayParihar33
requested review from
amitash1912,
ravibits and
saif-at-scalekit
as code owners
|
Note Reviews pausedIt looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the Use the following commands to manage reviews:
Use the checkboxes below for quick actions:
WalkthroughDocumentation reorganizes the "bring your own connector" area into an "add your own connector" workflow: removed the standalone managing-connectors page, consolidated management and curl flows into the auth-types-and-patterns page, added MCP support with a new Changes
Sequence Diagram(s)sequenceDiagram
rect rgba(200,230,255,0.5)
participant Client
end
rect rgba(220,255,200,0.5)
participant Scalekit
end
rect rgba(255,220,200,0.5)
participant UpstreamAPI
end
Client->>Scalekit: Trigger REST connector action (proxy request)
Scalekit->>UpstreamAPI: Proxy HTTP request with connector auth
UpstreamAPI-->>Scalekit: Response
Scalekit-->>Client: Return response
sequenceDiagram
rect rgba(200,230,255,0.5)
participant Client
end
rect rgba(220,255,200,0.5)
participant Scalekit
end
rect rgba(255,200,230,0.5)
participant MCPServer
end
rect rgba(255,220,200,0.5)
participant ToolRuntime
end
Client->>Scalekit: Trigger MCP connector action
Scalekit->>MCPServer: list_scoped_tools (discover tools)
MCPServer-->>Scalekit: Tool metadata
Scalekit->>ToolRuntime: execute_tool (invoke discovered tool)
ToolRuntime->>MCPServer: MCP executes upstream call
MCPServer-->>ToolRuntime: Execution result
ToolRuntime-->>Scalekit: Result
Scalekit-->>Client: Return result
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
✅ Deploy Preview for scalekit-starlight ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx`:
- Around line 143-237: Add missing Go and Java examples for both the discovery
(list_scoped_tools / listScopedTools) and execution (execute_tool / executeTool)
snippets so the page includes Node.js, Python, Go, and Java; use the same
variable names (scalekit / scalekit_client / connectionName / connection_name /
connectionNameGo / connectionNameJava and identifier) across all snippets, show
creating the Scalekit client (ScalekitClient / scalekit.client.ScalekitClient
equivalents), call list_scoped_tools/listScopedTools with the connection name
filter, and call execute_tool/executeTool via the actions client, mirroring the
inputs/outputs shown for Node.js and Python and keeping the Tabs/TabsItem
structure consistent with existing patterns.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: 0f99083a-dc99-4e6d-ac17-793f683473ed
📒 Files selected for processing (4)
src/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdxsrc/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: Redirect rules - scalekit-starlight
- GitHub Check: Header rules - scalekit-starlight
- GitHub Check: Pages changed - scalekit-starlight
🧰 Additional context used
📓 Path-based instructions (6)
**/*.mdx
📄 CodeRabbit inference engine (.cursorrules)
**/*.mdx: Use clear, descriptive titles that explain the purpose of the document
Include comprehensive descriptions in frontmatter metadata
Organize content with logical heading hierarchy (H2, H3, H4)
Use tableOfContents property in frontmatter when content has multiple sections
Set appropriate sidebar labels for navigation in frontmatter
Use direct instruction writing style with phrases like 'This guide shows you how to...' and 'Create an authorization URL to...'
Use second person perspective ('your application', 'you receive', 'you must') in documentation
Keep sentences concise, aiming for under 25 words per sentence
Explain the 'why' in documentation with phrases like 'This prevents CSRF attacks by...' or 'Use this to validate that...'
Use action verbs in section headings: 'Store session tokens securely', 'Validate the state parameter', 'Exchange authorization code for tokens'
Use present tense for descriptions: 'Scalekit handles the complex authentication flow', 'The SDK provides methods to refresh tokens'
Use future tense for results: 'This will redirect users to...', 'You'll receive a JWT containing...', 'Scalekit returns an authorization code'
Use transition phrases between sections: 'After the user authenticates...', 'Once the state is validated...', 'Let's take a look at how to...'
Write 1-3 opening paragraphs that explain what users will accomplish, provide context about when/why, preview key concepts, and use direct instructional language
Begin introduction sections with a clear statement of what the guide covers and explain the problem being solved
Use collapsible sections in introduction for sequence diagrams, video demonstrations, data models, and JSON examples with appropriate icons
Use numbered format within Steps component:1. ## Titlewith all step content indented with exactly 3 spaces
Use action-oriented headings in step-by-step guides within Steps components
Include code examples in all 4 languages (Node.js, Python, Go, Java) within Steps co...
Files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
⚙️ CodeRabbit configuration file
**/*.mdx: You are reviewing Scalekit developer documentation written in MDX
(Astro + Starlight framework). Apply ALL of the following checks:Frontmatter
titleMUST be ≤ 60 characters and clearly state what the page does.descriptionMUST be ≤ 160 characters, action-oriented, unique per page.sidebar.labelMUST be present and ≤ 30 characters.sidebar.orderMUST be set on every page that lives inside a section
with siblings, to enforce the journey order in sidebar.config.ts.- Flag any missing
prev/nextlinks on pages that are clearly
part of a sequential flow (e.g., quickstart → implement-login →
complete-login → manage-session → logout).Voice & Style (CLAUDE.md standards)
- Voice: confident, direct, collaborative, instructional.
- Person: second person only ("you", "your application"). Reject "we",
"our", "the developer", "the user".- Tense: present tense for descriptions; imperative mood for instructions.
- Flag weasel words: "simply", "just", "easy", "straightforward",
"obviously", "of course", "note that".- Flag passive voice constructions where active voice is clearer.
- Headings must be sentence case, not Title Case (except proper nouns).
- No heading should end with a colon or period.
Content structure
- Journey how-to guides MUST contain numbered
<Steps>(Starlight
component). This does NOT apply tosrc/content/docs/cookbooks/**
(blog-style recipes — optional<Steps>,<Tabs>after</Steps>OK;
see cookbookspath_instructions).- Concept pages MUST NOT contain numbered steps — concepts explain, not instruct.
- API reference pages MUST list parameters in a table with Name / Type /
Required / Description columns.- Every page MUST end with a clear "what's next" signal — either a
next:frontmatter link, a<LinkCard>, or an explicit paragraph
pointing the reader forward in the sidebar journey.Code examples
- ALL code examples that show SDK usage MUST include all four language
tabs...
Files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
**/*.{yml,yaml,md,mdx}
📄 CodeRabbit inference engine (.cursor/rules/browsecentral-labels.mdc)
**/*.{yml,yaml,md,mdx}: BrowseCentral labels should be maximum 3-5 words - keep concise but add context when needed
BrowseCentral labels should be action-oriented - start with verbs when possible
BrowseCentral labels should be specific and clear - add context when simple labels are ambiguous
BrowseCentral labels should be outcome-focused - describe what users accomplish and the context
BrowseCentral labels should use 'Action + Object' pattern (e.g., 'Invite users', 'Restrict sign-up', 'Set up SCIM')
BrowseCentral labels should use feature names (e.g., 'Enterprise SSO', 'Passwordless quickstart')
BrowseCentral labels should describe task completion (e.g., 'Run migrations', 'Migrate auth', 'Merge identities')
BrowseCentral labels should include specific context when needed (e.g., 'Configure Scalekit MCP server', 'Validate incoming API requests')
BrowseCentral labels should use integration context when applicable (e.g., 'Build MCP auth with your existing auth system')
BrowseCentral labels should avoid instructional prefixes: 'How to', 'Guide to', 'Implement', 'Configure', 'Learn', 'Understand'
BrowseCentral labels should avoid verbose phrases: 'Step-by-step guide', 'Complete tutorial', 'Detailed documentation'
BrowseCentral labels should avoid weak verbs: 'Enable', 'Allow', 'Provide', 'Support'
Files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
**/*.{md,mdx}
📄 CodeRabbit inference engine (.cursor/rules/deno-docs-style.mdc)
**/*.{md,mdx}: Use sentence case for all titles and headings in MD/MDX documentation
Keep page titles short and descriptive (3–7 words when possible) in MD/MDX documentation
Use outcome-focused headings that describe results, not categories (e.g., 'Run a script' not 'Scripts')
Avoid gerunds in headings when an imperative works - prefer 'Configure proxies' over 'Configuring proxies'
Keep sidebar labels concise (1–3 words), use sentence case, and focus on outcomes or objects
Use sentence case in sidebar labels without punctuation
Set frontmatter title in sentence case with a clear outcome; description in one sentence (≤160 chars); sidebar.label as shorter form of title; enable tableOfContents on longer pages
Start documentation pages with a one-paragraph overview explaining what the page covers and when to use it
Present the primary use case (80% path) first in documentation, with edge cases later
Use numbered steps for task-focused sections in documentation, with each step beginning with a verb
Break up long documentation sections with subheadings every 3–6 paragraphs
Use asides for important notes, tips, cautions, and references in documentation
Provide runnable, minimal code examples that work as-is in documentation
Prefer CLI-first examples and show file layout when helpful in documentation
Label code blocks with titles for context (e.g., 'Terminal', 'main.ts') in documentation
Keep code block annotations brief and purposeful - annotate only what matters
Use consistent variable and file names across a documentation page
Use descriptive link text in documentation (e.g., 'See permission flags' not 'click here')
Prefer relative links for internal documentation pages and include anchors for section references
Reference APIs consistently using backticks for code, file names, CLI flags, and endpoints
Use backticks for code, file names, CLI flags, and endpoints in documentation
Use lists for options and features in documentation; tables only when comparisons are cleare...
Files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
src/content/docs/**/*.mdx
📄 CodeRabbit inference engine (.cursor/rules/starlight-steps-tabs-structure.mdc)
src/content/docs/**/*.mdx: In MDX documentation files,<Steps>must contain one continuous ordered list. Wrap<Steps>around a normal Markdown ordered list such as1. ## ...
In MDX documentation files, numbered step lines must start at column 0. Do not indent the1. ##,2. ##, etc.
In MDX documentation files, any content that belongs to a step must be indented with 3 spaces: paragraphs, bullets, images,<Tabs>,<TabItem>, and fenced code blocks
In MDX documentation files, prefer plain Markdown inside<Steps>. If the content is mostly<Tabs>or other JSX-heavy blocks, use normal section headings instead of<Steps>
In MDX documentation files, when<Tabs>is used inside a step, keep<Tabs>,<TabItem>,</TabItem>, and</Tabs>consistently nested under that step
In MDX documentation files, if a tabs block is not part of a numbered step, place it outside</Steps>
Files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
src/content/docs/**/*.{md,mdx}
📄 CodeRabbit inference engine (CLAUDE.md)
src/content/docs/**/*.{md,mdx}: Every documentation page must include frontmatter with at least:title(≤60 chars),description(≤160 chars), andsidebar.label(1-3 words)
Use H2 for major sections, H3 for subsections, and H4 only inside<Steps>; never use H1 in body content and avoid nesting beyond H4
Use numbered lists only inside<Steps>for ordered procedures; use bulleted lists for unordered information
Use bold for first mention of important terms, UI elements, and dashboard paths; use inline code for technical identifiers (variables, functions, endpoints, scopes, environment variables, file paths, placeholders)
The<Steps>component requires a single continuous ordered list with proper indentation: steps at column 0, continuation content indented with exactly 3 spaces
Use<Aside>component with atitleattribute for cautions, tips, and notes
Use<Badge>component to indicate parameter requirements in tables and inline text
Use<details>blocks at the end of pages for FAQs, common scenarios, and troubleshooting
Split content into clear sections with descriptive, sentence-style titles; include a table of contents for documents with multiple sections; keep paragraphs short and isolate critical points in their own short paragraphs
Begin sections and paragraphs with standalone topic sentences that preview content; put topic words at the beginning to support fast skimming; put key takeaways and results at the top of documents
Use bullets and tables generously to structure information; bold important text to highlight key concepts and decisions
Keep sentences simple, right-branching, and unambiguous; avoid ambiguous noun stacks and demonstrative pronouns like 'this' or 'that' when the referent is not explicit
Maintain strict consistency in terminology, formatting, and style; do not presume the reader's state of mind or intentions; use direct, instructional language
Write more simply than you think you need to; optimize for readers new to the do...
Files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
src/content/docs/agentkit/**/*.{md,mdx}
📄 CodeRabbit inference engine (CLAUDE.md)
Agentkit code examples live in the external repo scalekit-developers/agent-auth-examples organized as
javascript/frameworks/<framework>andpython/frameworks/<framework>; verify docs snippets match current implementations in that repo
Files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
🧠 Learnings (34)
📓 Common learnings
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 529
File: src/content/docs/agent-auth/mcp/tool-access-via-mcp.mdx:188-190
Timestamp: 2026-03-25T10:15:02.544Z
Learning: In scalekit-inc/developer-docs, the Aside note in `src/content/docs/agent-auth/mcp/tool-access-via-mcp.mdx` warning that ChatGPT's beta MCP connector "may not work correctly" and "does not fully implement the MCP specification" is intentional. Real-world developers have reported re-auth loops and inconsistent streamable HTTP behaviour with ChatGPT compared to Claude, even though OpenAI's marketing describes it as "full MCP support". Do not flag or suggest removing this compatibility warning in future reviews.
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 0
File: :0-0
Timestamp: 2026-03-13T04:24:59.653Z
Learning: In scalekit-inc/developer-docs, for PRs focused on tooling and templatizing (e.g., extracting usage sections into reusable MDX templates and updating sync scripts), review comments about .mdx file content quality (casing, unused imports, import consolidation, endpoint descriptions, etc.) are considered out of scope and should be resolved without blocking the PR.
Learnt from: CR
Repo: scalekit-inc/developer-docs PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-20T11:29:40.242Z
Learning: Product-based documentation (MCP Auth, Agent Auth, Full Stack Auth, Modular SCIM, Modular SSO) must follow a journey-focused approach representing a developer's journey toward implementing authentication
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 577
File: src/content/docs/mcp/auth-methods/custom-auth.mdx:207-212
Timestamp: 2026-04-08T15:23:40.627Z
Learning: In `src/content/docs/mcp/auth-methods/custom-auth.mdx` (BYOA MCP custom auth, MCP section), the `roles` and `custom_attributes` fields in the `updateLoginUserDetails` / Update Login User Details call are not yet supported in the Python, Node.js, and Go SDKs. These fields currently appear only in the cURL tab example. Do not require or flag the absence of `roles` and `custom_attributes` in the Python/Node.js/Go SDK snippets until the SDKs are updated to support these fields.
Learnt from: CR
Repo: scalekit-inc/developer-docs PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-04-20T11:30:52.410Z
Learning: Product-based documentation (MCP Auth, Agent Auth, Full Stack Auth, Modular SCIM, Modular SSO) MUST follow a journey-focused approach. Each product represents a developer's journey toward implementing authentication in their projects
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/googlesheets.mdx:95-141
Timestamp: 2026-02-26T07:22:55.583Z
Learning: For MDX files under src/content/docs/reference/agent-connectors/, the parameter tables (showing tool properties) are auto-generated from JSON API responses by scripts/sync-agent-connectors.js. Any table format corrections must be made in the generation script, not by manually editing the generated MDX files. The script should be updated to output the required "Name | Type | Required | Description" four-column table format per coding guidelines.
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 455
File: src/content/docs/reference/agent-connectors/asana.mdx:94-173
Timestamp: 2026-03-03T13:35:56.400Z
Learning: For Agent Connectors documentation (src/content/docs/reference/agent-connectors/**/*.mdx), currently only Python SDK support is available for Agent Actions/Agent Connectors. Do not require or enforce the multi-language SDK code examples (Node.js, Python, Go, Java) guideline for these connector docs until SDK support is ready in other languages. The Node.js, Go, and Java examples can be added once the respective SDKs support Agent Actions features.
Learnt from: dhaneshbs
Repo: scalekit-inc/developer-docs PR: 487
File: src/content/docs/agent-auth/connections.mdx:0-0
Timestamp: 2026-03-12T05:02:13.454Z
Learning: In `src/content/docs/agent-auth/connections.mdx` (and Agent Auth docs generally), custom authentication (username/password/bearer-token flows) is intentionally out of scope for the current Agent Auth release. Do not flag the absence of custom authentication connection type documentation in Agent Auth connection-type sections.
Learnt from: dhaneshbs
Repo: scalekit-inc/developer-docs PR: 487
File: src/content/docs/agent-auth/connections.mdx:0-0
Timestamp: 2026-03-12T05:02:13.454Z
Learning: In `src/content/docs/agent-auth/connections.mdx` (and Agent Auth docs in general), custom authentication (username/password/bearer-token flows) is intentionally out of scope for the current Agent Auth release. Do not flag the absence of custom authentication documentation in Agent Auth connection-type sections.
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/microsoftword.mdx:3-3
Timestamp: 2026-02-26T07:23:27.672Z
Learning: For MDX files under src/content/docs/reference/agent-connectors/, do not enforce the 160-character description limit. These files are auto-generated from API payloads via scripts/sync-agent-connectors.js and may have longer descriptions from the source data.
📚 Learning: 2026-02-26T07:22:55.583Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/googlesheets.mdx:95-141
Timestamp: 2026-02-26T07:22:55.583Z
Learning: For MDX files under src/content/docs/reference/agent-connectors/, the parameter tables (showing tool properties) are auto-generated from JSON API responses by scripts/sync-agent-connectors.js. Any table format corrections must be made in the generation script, not by manually editing the generated MDX files. The script should be updated to output the required "Name | Type | Required | Description" four-column table format per coding guidelines.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-02-26T07:18:51.377Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: scripts/sync-agent-connectors.js:0-0
Timestamp: 2026-02-26T07:18:51.377Z
Learning: In src/content/docs/reference/agent-connectors/**/*.mdx files, sidebar.label frontmatter is not required because the sidebar configuration references the agent-connectors directory for auto-generation. Navigation ordering and grouping are managed centrally in the sidebar configuration file.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-02-26T07:20:46.903Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/googlemeet.mdx:1-87
Timestamp: 2026-02-26T07:20:46.903Z
Learning: For auto-generated agent connector documentation pages in src/content/docs/reference/agent-connectors/, the "what's next" signal requirement (next: frontmatter link, <LinkCard>, or concluding paragraph) does not apply. These are reference pages generated by scripts/sync-agent-connectors.js and serve as lookup resources rather than sequential guides.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-02-26T07:21:37.207Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/googlesheets.mdx:89-131
Timestamp: 2026-02-26T07:21:37.207Z
Learning: In src/content/docs/reference/agent-connectors/** MDX files, tool headings (e.g., `googlesheets_create_spreadsheet`, `googlesheets_get_values`) intentionally use H2 (##) instead of H3 to ensure they appear in the table of contents for easier navigation. This is a deliberate UX choice for agent connector reference pages and should not be flagged as a hierarchy issue.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx
📚 Learning: 2026-02-26T07:23:27.672Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/microsoftword.mdx:3-3
Timestamp: 2026-02-26T07:23:27.672Z
Learning: For MDX files under src/content/docs/reference/agent-connectors/, do not enforce the 160-character description limit. These files are auto-generated from API payloads via scripts/sync-agent-connectors.js and may have longer descriptions from the source data.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-13T03:44:23.786Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 489
File: src/content/docs/reference/agent-connectors/youtube.mdx:19-26
Timestamp: 2026-03-13T03:44:23.786Z
Learning: In src/content/docs/reference/agent-connectors/*.mdx files, small raw HTML <div> blocks used for the connector header grid layout (e.g., a 5-column grid with description and logo) are considered readable without a justification comment. Do not flag the absence of a justification comment on these simple connector-header div blocks in agent-connector reference pages.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-04-13T10:43:05.628Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 590
File: src/components/templates/agent-connectors/_usage-databricks.mdx:83-83
Timestamp: 2026-04-13T10:43:05.628Z
Learning: In `src/components/templates/agent-connectors/_usage-*.mdx` files, the trailing `## Scalekit Tools` heading at the end of every usage template is intentional and consistent across all 42+ connector usage templates. It acts as a structural anchor/separator that the parent connector reference page uses to append the tool-list section beneath the proxy API examples. Do not flag this heading as empty or duplicate in future reviews of these template files.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-04-20T17:03:02.786Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 619
File: src/components/templates/agent-connectors/_usage-posthogmcp.mdx:82-82
Timestamp: 2026-04-20T17:03:02.786Z
Learning: In `src/components/templates/agent-connectors/_usage-posthogmcp.mdx`, the trailing `## Scalekit Tools` heading is intentionally omitted. The parent connector page (`src/content/docs/agentkit/connectors/posthogmcp.mdx`) renders the tool list separately via the `ToolList` component and the imported `tools` dataset, so the structural anchor heading used by other `_usage-*.mdx` templates is not needed here. Do not flag the missing `## Scalekit Tools` heading in this file.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-12T16:28:42.817Z
Learnt from: Pranesh-Raghu
Repo: scalekit-inc/developer-docs PR: 483
File: src/components/templates/agent-connectors/_setup-zendesk.mdx:20-20
Timestamp: 2026-03-12T16:28:42.817Z
Learning: In src/components/templates/agent-connectors/_setup-*.mdx files, using plain Markdown link syntax (e.g., [Scalekit dashboard](https://app.scalekit.com)) for external links is acceptable and intentional. Do not flag the absence of target="_blank" and rel="noopener" attributes in these agent-connector setup template files. This follows the established pattern across all connector templates in this directory.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-12T16:29:16.422Z
Learnt from: Pranesh-Raghu
Repo: scalekit-inc/developer-docs PR: 483
File: src/components/templates/agent-connectors/_setup-onenote.mdx:12-12
Timestamp: 2026-03-12T16:29:16.422Z
Learning: In src/components/templates/agent-connectors/_setup-*.mdx files, using "Azure Active Directory" instead of the rebranded "Microsoft Entra ID" is acceptable and intentional. Do not flag "Azure Active Directory" as outdated branding in these agent-connector setup template files.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdx
📚 Learning: 2026-03-13T03:51:44.897Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 489
File: src/content/docs/reference/agent-connectors/attio.mdx:24-24
Timestamp: 2026-03-13T03:51:44.897Z
Learning: For any agent connector documentation files located in src/content/docs/reference/agent-connectors/, use CDN URLs for connector logos with the host `https://cdn.scalekit.com/sk-connect/assets/provider-icons/` (e.g., `https://cdn.scalekit.com/sk-connect/assets/provider-icons/attio.svg`). The correct host is `cdn.scalekit.com`, NOT `cdn.scalekit.cloud`. Do not flag or change image src attributes that use `cdn.scalekit.com` for provider icons in this directory.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-04-20T11:29:40.242Z
Learnt from: CR
Repo: scalekit-inc/developer-docs PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-20T11:29:40.242Z
Learning: Product-based documentation (MCP Auth, Agent Auth, Full Stack Auth, Modular SCIM, Modular SSO) must follow a journey-focused approach representing a developer's journey toward implementing authentication
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-01-30T18:18:50.883Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 415
File: src/content/docs/authenticate/fsa/multiapp/manage-apps.mdx:31-49
Timestamp: 2026-01-30T18:18:50.883Z
Learning: In all Scalekit documentation files (MDX), treat the terms 'Applications', 'Single Page Application (SPA)', 'Native Application', and 'Web Application' as proper nouns and preserve their capitalization in headings and body text. Ensure these terms remain capitalized even when used in sentence case or within prose.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-02-04T12:47:16.544Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 412
File: src/content/docs/dev-kit/tools/scalekit-dryrun.mdx:1-23
Timestamp: 2026-02-04T12:47:16.544Z
Learning: In scalekit-inc/developer-docs, the MDX frontmatter field order is required only when the sidebar configuration points to a directory (for auto-generation). If the sidebar.config.ts references a specific file path, the order field is not required. Apply this check to all MDX files under src/content/docs: if a file contributes to an auto-generated sidebar (directory path), ensure order is present; if it’s linked to a concrete file, order can be omitted. Use sidebar.config.ts to determine whether a given MDX file falls under directory-based vs file-specific sidebar references.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-02-25T08:57:12.201Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 444
File: src/content/docs/agent-auth/quickstart.mdx:2-10
Timestamp: 2026-02-25T08:57:12.201Z
Learning: In Scalekit developer-docs (Astro Starlight), do not auto-suggest adding tableOfContents in frontmatter unless the user explicitly overrides the default behavior. The default enables tableOfContents with minHeadingLevel 2 and maxHeadingLevel 3. Only set tableOfContents when you want to customize heading levels or disable it entirely; otherwise omit it for other docs.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-02-25T13:04:27.491Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 444
File: src/content/docs/agent-auth/start-agent-auth-coding-agents.mdx:9-17
Timestamp: 2026-02-25T13:04:27.491Z
Learning: Allow page-level CSS overrides in MDX frontmatter (head: style) for readability and engagement, even if it customizes typography beyond defaults. This applies to per-page UX decisions, including heading sizes and style tweaks, but keep overrides purposeful, accessible, and within the repository's design guidelines. Use these overrides sparingly and document the rationale for maintainability.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-05T11:29:08.125Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 463
File: src/content/docs/agent-auth/providers.mdx:35-73
Timestamp: 2026-03-05T11:29:08.125Z
Learning: In src/content/docs/agent-auth/providers.mdx, the Card components intentionally use icon=" " (a space) to render consistent colored boxes since some Starlight icon names resolve to icons and others do not. Do not flag icon=" " as a placeholder issue for this file; treat this as a deliberate UX choice specific to this MDX page and avoid raising a placeholder-icon warning here.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-09T07:27:56.794Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 469
File: src/content/docs/guides/integrations/scim-integrations/azure-scim.mdx:95-107
Timestamp: 2026-03-09T07:27:56.794Z
Learning: Do not enforce the 3-space indentation rule for Steps component content as a hard style rule in MDX files under src/content/docs/**/*.mdx. Only flag/rectify it if it causes visible rendering problems in the UI. Otherwise, allow current formatting; apply this rule only when rendering issues are observed and document any fixes.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-09T07:32:38.426Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 467
File: src/content/docs/sso/guides/sso-user-attributes.mdx:108-148
Timestamp: 2026-03-09T07:32:38.426Z
Learning: In MDX code samples under src/content/docs (and similar conceptual snippets in scalekit-inc/developer-docs), when an example's sole purpose is to show how to access a specific value (e.g., reading JWT claims after token validation), omit error/non-happy-path handling to keep the snippet focused. Do not flag the absence of error paths in narrowly scoped conceptual snippets.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-17T16:01:50.487Z
Learnt from: dhaneshbs
Repo: scalekit-inc/developer-docs PR: 506
File: src/content/docs/authenticate/fsa/quickstart.mdx:851-853
Timestamp: 2026-03-17T16:01:50.487Z
Learning: In the Scalekit Python SDK docs, clarify that LogoutUrlOptions is not exported from the top-level scalekit package __init__.py. The correct import path in code samples or reviews is: from scalekit.common.scalekit import LogoutUrlOptions. Do not flag this import path as incorrect in documentation or code reviews; ensure examples reflect the proper import path to avoid confusion for users.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-02-25T03:34:41.147Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 444
File: src/content/docs/agent-auth/start-agent-auth-coding-agents.mdx:31-31
Timestamp: 2026-02-25T03:34:41.147Z
Learning: In MDX files, import { Code } from 'astrojs/starlight/components' only if the MDX content actually uses the <Code> component. If the file uses only fenced code blocks (```), the import is not required. Apply this guideline to all MDX files (e.g., src/content/docs/**/*.mdx) to avoid unnecessary imports and reduce bundle size.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-02-25T18:41:00.639Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 446
File: src/content/docs/authenticate/m2m/api-auth-quickstart.mdx:78-78
Timestamp: 2026-02-25T18:41:00.639Z
Learning: Preserve full URLs inside code comments in MDX code blocks (bash/python/js) when the URLs are part of copyable examples. Do not flag these in code examples. Use relative paths in prose and hyperlinks within MDX; only enforce relative paths for markdown prose links, not for URLs inside code comments.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-03T13:35:56.400Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 455
File: src/content/docs/reference/agent-connectors/asana.mdx:94-173
Timestamp: 2026-03-03T13:35:56.400Z
Learning: For Agent Connectors documentation (src/content/docs/reference/agent-connectors/**/*.mdx), currently only Python SDK support is available for Agent Actions/Agent Connectors. Do not require or enforce the multi-language SDK code examples (Node.js, Python, Go, Java) guideline for these connector docs until SDK support is ready in other languages. The Node.js, Go, and Java examples can be added once the respective SDKs support Agent Actions features.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx
📚 Learning: 2026-03-12T05:02:13.454Z
Learnt from: dhaneshbs
Repo: scalekit-inc/developer-docs PR: 487
File: src/content/docs/agent-auth/connections.mdx:0-0
Timestamp: 2026-03-12T05:02:13.454Z
Learning: In `src/content/docs/agent-auth/connections.mdx` (and Agent Auth docs generally), custom authentication (username/password/bearer-token flows) is intentionally out of scope for the current Agent Auth release. Do not flag the absence of custom authentication connection type documentation in Agent Auth connection-type sections.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-12T05:02:13.454Z
Learnt from: dhaneshbs
Repo: scalekit-inc/developer-docs PR: 487
File: src/content/docs/agent-auth/connections.mdx:0-0
Timestamp: 2026-03-12T05:02:13.454Z
Learning: In `src/content/docs/agent-auth/connections.mdx` (and Agent Auth docs in general), custom authentication (username/password/bearer-token flows) is intentionally out of scope for the current Agent Auth release. Do not flag the absence of custom authentication documentation in Agent Auth connection-type sections.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-25T10:15:02.544Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 529
File: src/content/docs/agent-auth/mcp/tool-access-via-mcp.mdx:188-190
Timestamp: 2026-03-25T10:15:02.544Z
Learning: In scalekit-inc/developer-docs, the Aside note in `src/content/docs/agent-auth/mcp/tool-access-via-mcp.mdx` warning that ChatGPT's beta MCP connector "may not work correctly" and "does not fully implement the MCP specification" is intentional. Real-world developers have reported re-auth loops and inconsistent streamable HTTP behaviour with ChatGPT compared to Claude, even though OpenAI's marketing describes it as "full MCP support". Do not flag or suggest removing this compatibility warning in future reviews.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-25T15:59:51.911Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 531
File: src/components/templates/agent-connectors/_usage-granolamcp.mdx:18-48
Timestamp: 2026-03-25T15:59:51.911Z
Learning: In `src/components/templates/agent-connectors/_usage-*.mdx` files (agent-connector usage templates, e.g., `_usage-granolamcp.mdx`), code examples are intentionally directional/illustrative and are meant to show the call sequence pattern rather than production-ready runnable code. Do not flag the absence of try/except or try/catch error handling in these usage template files.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx
📚 Learning: 2026-04-13T14:22:37.194Z
Learnt from: Pranesh-Raghu
Repo: scalekit-inc/developer-docs PR: 591
File: src/content/docs/reference/agent-connectors/calendly.mdx:47-47
Timestamp: 2026-04-13T14:22:37.194Z
Learning: In `src/content/docs/reference/agent-connectors/` MDX files (agent-connector reference pages, e.g., calendly.mdx), the `title` attribute on `<Aside>` components is not required. Do not flag missing `title` props on `<Aside>` components in files under this directory. This is a deliberate exception to the global rule requiring `title` on all `<Aside>` components.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-03-25T16:00:29.351Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 531
File: src/content/docs/reference/agent-connectors/granolamcp.mdx:52-58
Timestamp: 2026-03-25T16:00:29.351Z
Learning: In `src/content/docs/reference/agent-connectors/**` (agent-connector reference pages, e.g., granolamcp.mdx), short sequential setup steps (4 items or fewer) may use plain Markdown numbered lists instead of the Starlight `<Steps>` component to avoid visual clutter when the page already contains multiple structured content blocks (tables, details/summary blocks, tool sections). Do not flag or require `<Steps>` for these short setup procedures on agent-connector reference pages.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx
📚 Learning: 2026-03-10T10:37:49.873Z
Learnt from: Pranesh-Raghu
Repo: scalekit-inc/developer-docs PR: 475
File: src/components/templates/agent-connectors/_setup-asana.mdx:15-15
Timestamp: 2026-03-10T10:37:49.873Z
Learning: In `src/components/templates/agent-connectors/`, all connector setup MDX files (e.g., _setup-asana.mdx, _setup-clickup.mdx, _setup-confluence.mdx, _setup-googlecalendar.mdx, _setup-intercom.mdx, _setup-monday.mdx, _setup-notion.mdx, _setup-zoom.mdx) intentionally use a single shared redirect URI screenshot (`use-own-credentials-redirect-uri.png` located under `@/assets/docs/agent-connectors/<connector-name>/`) for all redirect URI-related steps, even when steps show different UIs (e.g., Scalekit dashboard vs. the third-party console). Do not flag reuse of this image across multiple steps within the same connector file as an issue.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-04-20T11:29:40.242Z
Learnt from: CR
Repo: scalekit-inc/developer-docs PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-20T11:29:40.242Z
Learning: Applies to src/content/docs/agentkit/**/*.{md,mdx} : Agentkit code examples live in the external repo **scalekit-developers/agent-auth-examples** organized as `javascript/frameworks/<framework>` and `python/frameworks/<framework>`; verify docs snippets match current implementations in that repo
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-04-08T15:23:40.627Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 577
File: src/content/docs/mcp/auth-methods/custom-auth.mdx:207-212
Timestamp: 2026-04-08T15:23:40.627Z
Learning: In `src/content/docs/mcp/auth-methods/custom-auth.mdx` (BYOA MCP custom auth, MCP section), the `roles` and `custom_attributes` fields in the `updateLoginUserDetails` / Update Login User Details call are not yet supported in the Python, Node.js, and Go SDKs. These fields currently appear only in the cURL tab example. Do not require or flag the absence of `roles` and `custom_attributes` in the Python/Node.js/Go SDK snippets until the SDKs are updated to support these fields.
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
📚 Learning: 2026-04-20T11:30:52.410Z
Learnt from: CR
Repo: scalekit-inc/developer-docs PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-04-20T11:30:52.410Z
Learning: Product-based documentation (MCP Auth, Agent Auth, Full Stack Auth, Modular SCIM, Modular SSO) MUST follow a journey-focused approach. Each product represents a developer's journey toward implementing authentication in their projects
Applied to files:
src/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx
🔇 Additional comments (4)
src/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdx (1)
58-59: Good expansion for MCP routing and payload parity.The new
is_mcpguidance and the four MCP payload examples are clear and operationally useful. The final checklist update also reduces configuration mistakes before create/update calls.Also applies to: 199-206, 207-327, 337-337
src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdx (1)
13-14: Navigation and MCP request-body guidance are aligned and clear.The updated next label and the MCP payload callout keep the flow consistent with the new auth-patterns split while preserving endpoint behavior clarity.
Also applies to: 55-55
src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx (1)
2-3: Strong runtime split and section routing.The REST-vs-MCP framing is easy to follow, and the aside directs readers to the correct execution path quickly.
Also applies to: 19-30, 51-54, 135-142
src/content/docs/agentkit/bring-your-own-connector/overview.mdx (1)
19-24: Overview updates are cohesive with the new REST + MCP model.The revised intro, benefits list, runtime note, and final workflow step stay aligned and keep the journey clear for both connector types.
Also applies to: 34-40, 50-52
Renamed pages for clarity, merged auth-types-and-patterns with managing-connectors content to eliminate duplication, improved wording and navigation throughout. Updated redirects and sidebar configuration.
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@src/content/docs/agentkit/bring-your-own-connector/overview.mdx`:
- Line 26: The lead-in sentence "Add your own connector lets you:" is
grammatically incorrect; change it to a proper gerund or imperative phrase such
as "Adding your own connector lets you:" or "Add your own connector:" in the
file (the line currently containing the exact text "Add your own connector lets
you:") so the section reads smoothly and correctly.
In `@src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx`:
- Around line 197-227: Make the examples self-contained by adding client
initialization and env loading, using variables for the connection and
identifier, and adding simple error handling: instantiate ScalekitClient (Node)
/ scalekit.client.ScalekitClient (Python) with env vars, set
connectionName/connection_name and identifier variables, pass those variables to
actions.executeTool/execute_tool instead of hard-coded strings, and wrap the
call in a try/catch (Node) / try/except (Python) that logs the error; locate
these changes around the use of scalekit/scalekit_client, actions,
executeTool/execute_tool, connectionName/connection_name, and identifier.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: 7708f86a-b0ac-4f49-9c4e-782559ee3ae6
📒 Files selected for processing (9)
src/configs/redirects.config.tssrc/configs/sidebar.config.tssrc/content/docs/agentkit/advanced/custom-domain.mdxsrc/content/docs/agentkit/advanced/launch-checklist.mdxsrc/content/docs/agentkit/bring-your-own-connector/auth-types-and-patterns.mdxsrc/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdxsrc/content/docs/agentkit/bring-your-own-connector/overview.mdxsrc/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdxsrc/content/docs/agentkit/connectors/index.mdx
💤 Files with no reviewable changes (2)
- src/configs/sidebar.config.ts
- src/content/docs/agentkit/bring-your-own-connector/managing-connectors.mdx
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx`:
- Line 55: Update the external link for "Scalekit Dashboard" in
scalekit-optimized-tools.mdx to include secure external-link attributes by
adding target="_blank" and rel="noopener" to the anchor element; locate the
anchor text "Scalekit Dashboard" and modify its tag so the link opens in a new
tab with rel="noopener" for security.
- Around line 59-63: Update the prose that describes how to identify a connected
account for execute_tool / executeTool to explicitly map parameter names by
language: state that Python clients use identifier + connection_name, while
Node.js clients use identifier + connector; mention both examples shown (e.g.,
the Node.js example using connector: 'gmail' and the Python example using
connection_name: "gmail") and replace the ambiguous phrase "Connection name ...
(`connection_name`)" with this language-specific mapping so readers know which
parameter to pass per SDK.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: ce6d7721-3994-4707-8cb5-4d4e64fa3130
📒 Files selected for processing (1)
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: Redirect rules - scalekit-starlight
- GitHub Check: Header rules - scalekit-starlight
- GitHub Check: Pages changed - scalekit-starlight
🧰 Additional context used
📓 Path-based instructions (6)
**/*.mdx
📄 CodeRabbit inference engine (.cursorrules)
**/*.mdx: Use clear, descriptive titles that explain the purpose of the document
Include comprehensive descriptions in frontmatter metadata
Organize content with logical heading hierarchy (H2, H3, H4)
Use tableOfContents property in frontmatter when content has multiple sections
Set appropriate sidebar labels for navigation in frontmatter
Use direct instruction writing style with phrases like 'This guide shows you how to...' and 'Create an authorization URL to...'
Use second person perspective ('your application', 'you receive', 'you must') in documentation
Keep sentences concise, aiming for under 25 words per sentence
Explain the 'why' in documentation with phrases like 'This prevents CSRF attacks by...' or 'Use this to validate that...'
Use action verbs in section headings: 'Store session tokens securely', 'Validate the state parameter', 'Exchange authorization code for tokens'
Use present tense for descriptions: 'Scalekit handles the complex authentication flow', 'The SDK provides methods to refresh tokens'
Use future tense for results: 'This will redirect users to...', 'You'll receive a JWT containing...', 'Scalekit returns an authorization code'
Use transition phrases between sections: 'After the user authenticates...', 'Once the state is validated...', 'Let's take a look at how to...'
Write 1-3 opening paragraphs that explain what users will accomplish, provide context about when/why, preview key concepts, and use direct instructional language
Begin introduction sections with a clear statement of what the guide covers and explain the problem being solved
Use collapsible sections in introduction for sequence diagrams, video demonstrations, data models, and JSON examples with appropriate icons
Use numbered format within Steps component:1. ## Titlewith all step content indented with exactly 3 spaces
Use action-oriented headings in step-by-step guides within Steps components
Include code examples in all 4 languages (Node.js, Python, Go, Java) within Steps co...
Files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
⚙️ CodeRabbit configuration file
**/*.mdx: You are reviewing Scalekit developer documentation written in MDX
(Astro + Starlight framework). Apply ALL of the following checks:Frontmatter
titleMUST be ≤ 60 characters and clearly state what the page does.descriptionMUST be ≤ 160 characters, action-oriented, unique per page.sidebar.labelMUST be present and ≤ 30 characters.sidebar.orderMUST be set on every page that lives inside a section
with siblings, to enforce the journey order in sidebar.config.ts.- Flag any missing
prev/nextlinks on pages that are clearly
part of a sequential flow (e.g., quickstart → implement-login →
complete-login → manage-session → logout).Voice & Style (CLAUDE.md standards)
- Voice: confident, direct, collaborative, instructional.
- Person: second person only ("you", "your application"). Reject "we",
"our", "the developer", "the user".- Tense: present tense for descriptions; imperative mood for instructions.
- Flag weasel words: "simply", "just", "easy", "straightforward",
"obviously", "of course", "note that".- Flag passive voice constructions where active voice is clearer.
- Headings must be sentence case, not Title Case (except proper nouns).
- No heading should end with a colon or period.
Content structure
- Journey how-to guides MUST contain numbered
<Steps>(Starlight
component). This does NOT apply tosrc/content/docs/cookbooks/**
(blog-style recipes — optional<Steps>,<Tabs>after</Steps>OK;
see cookbookspath_instructions).- Concept pages MUST NOT contain numbered steps — concepts explain, not instruct.
- API reference pages MUST list parameters in a table with Name / Type /
Required / Description columns.- Every page MUST end with a clear "what's next" signal — either a
next:frontmatter link, a<LinkCard>, or an explicit paragraph
pointing the reader forward in the sidebar journey.Code examples
- ALL code examples that show SDK usage MUST include all four language
tabs...
Files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
**/*.{yml,yaml,md,mdx}
📄 CodeRabbit inference engine (.cursor/rules/browsecentral-labels.mdc)
**/*.{yml,yaml,md,mdx}: BrowseCentral labels should be maximum 3-5 words - keep concise but add context when needed
BrowseCentral labels should be action-oriented - start with verbs when possible
BrowseCentral labels should be specific and clear - add context when simple labels are ambiguous
BrowseCentral labels should be outcome-focused - describe what users accomplish and the context
BrowseCentral labels should use 'Action + Object' pattern (e.g., 'Invite users', 'Restrict sign-up', 'Set up SCIM')
BrowseCentral labels should use feature names (e.g., 'Enterprise SSO', 'Passwordless quickstart')
BrowseCentral labels should describe task completion (e.g., 'Run migrations', 'Migrate auth', 'Merge identities')
BrowseCentral labels should include specific context when needed (e.g., 'Configure Scalekit MCP server', 'Validate incoming API requests')
BrowseCentral labels should use integration context when applicable (e.g., 'Build MCP auth with your existing auth system')
BrowseCentral labels should avoid instructional prefixes: 'How to', 'Guide to', 'Implement', 'Configure', 'Learn', 'Understand'
BrowseCentral labels should avoid verbose phrases: 'Step-by-step guide', 'Complete tutorial', 'Detailed documentation'
BrowseCentral labels should avoid weak verbs: 'Enable', 'Allow', 'Provide', 'Support'
Files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
**/*.{md,mdx}
📄 CodeRabbit inference engine (.cursor/rules/deno-docs-style.mdc)
**/*.{md,mdx}: Use sentence case for all titles and headings in MD/MDX documentation
Keep page titles short and descriptive (3–7 words when possible) in MD/MDX documentation
Use outcome-focused headings that describe results, not categories (e.g., 'Run a script' not 'Scripts')
Avoid gerunds in headings when an imperative works - prefer 'Configure proxies' over 'Configuring proxies'
Keep sidebar labels concise (1–3 words), use sentence case, and focus on outcomes or objects
Use sentence case in sidebar labels without punctuation
Set frontmatter title in sentence case with a clear outcome; description in one sentence (≤160 chars); sidebar.label as shorter form of title; enable tableOfContents on longer pages
Start documentation pages with a one-paragraph overview explaining what the page covers and when to use it
Present the primary use case (80% path) first in documentation, with edge cases later
Use numbered steps for task-focused sections in documentation, with each step beginning with a verb
Break up long documentation sections with subheadings every 3–6 paragraphs
Use asides for important notes, tips, cautions, and references in documentation
Provide runnable, minimal code examples that work as-is in documentation
Prefer CLI-first examples and show file layout when helpful in documentation
Label code blocks with titles for context (e.g., 'Terminal', 'main.ts') in documentation
Keep code block annotations brief and purposeful - annotate only what matters
Use consistent variable and file names across a documentation page
Use descriptive link text in documentation (e.g., 'See permission flags' not 'click here')
Prefer relative links for internal documentation pages and include anchors for section references
Reference APIs consistently using backticks for code, file names, CLI flags, and endpoints
Use backticks for code, file names, CLI flags, and endpoints in documentation
Use lists for options and features in documentation; tables only when comparisons are cleare...
Files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
src/content/docs/**/*.mdx
📄 CodeRabbit inference engine (.cursor/rules/starlight-steps-tabs-structure.mdc)
src/content/docs/**/*.mdx: In MDX documentation files,<Steps>must contain one continuous ordered list. Wrap<Steps>around a normal Markdown ordered list such as1. ## ...
In MDX documentation files, numbered step lines must start at column 0. Do not indent the1. ##,2. ##, etc.
In MDX documentation files, any content that belongs to a step must be indented with 3 spaces: paragraphs, bullets, images,<Tabs>,<TabItem>, and fenced code blocks
In MDX documentation files, prefer plain Markdown inside<Steps>. If the content is mostly<Tabs>or other JSX-heavy blocks, use normal section headings instead of<Steps>
In MDX documentation files, when<Tabs>is used inside a step, keep<Tabs>,<TabItem>,</TabItem>, and</Tabs>consistently nested under that step
In MDX documentation files, if a tabs block is not part of a numbered step, place it outside</Steps>
Files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
src/content/docs/**/*.{md,mdx}
📄 CodeRabbit inference engine (CLAUDE.md)
src/content/docs/**/*.{md,mdx}: Every documentation page must include frontmatter with at least:title(≤60 chars),description(≤160 chars), andsidebar.label(1-3 words)
Use H2 for major sections, H3 for subsections, and H4 only inside<Steps>; never use H1 in body content and avoid nesting beyond H4
Use numbered lists only inside<Steps>for ordered procedures; use bulleted lists for unordered information
Use bold for first mention of important terms, UI elements, and dashboard paths; use inline code for technical identifiers (variables, functions, endpoints, scopes, environment variables, file paths, placeholders)
The<Steps>component requires a single continuous ordered list with proper indentation: steps at column 0, continuation content indented with exactly 3 spaces
Use<Aside>component with atitleattribute for cautions, tips, and notes
Use<Badge>component to indicate parameter requirements in tables and inline text
Use<details>blocks at the end of pages for FAQs, common scenarios, and troubleshooting
Split content into clear sections with descriptive, sentence-style titles; include a table of contents for documents with multiple sections; keep paragraphs short and isolate critical points in their own short paragraphs
Begin sections and paragraphs with standalone topic sentences that preview content; put topic words at the beginning to support fast skimming; put key takeaways and results at the top of documents
Use bullets and tables generously to structure information; bold important text to highlight key concepts and decisions
Keep sentences simple, right-branching, and unambiguous; avoid ambiguous noun stacks and demonstrative pronouns like 'this' or 'that' when the referent is not explicit
Maintain strict consistency in terminology, formatting, and style; do not presume the reader's state of mind or intentions; use direct, instructional language
Write more simply than you think you need to; optimize for readers new to the do...
Files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
src/content/docs/agentkit/**/*.{md,mdx}
📄 CodeRabbit inference engine (CLAUDE.md)
Agentkit code examples live in the external repo scalekit-developers/agent-auth-examples organized as
javascript/frameworks/<framework>andpython/frameworks/<framework>; verify docs snippets match current implementations in that repo
Files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
🧠 Learnings (24)
📓 Common learnings
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 623
File: src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx:197-227
Timestamp: 2026-04-22T09:58:57.649Z
Learning: In `src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx`, the `execute_tool` code examples (Node.js and Python) under the "MCP tool calling" section intentionally omit client initialization boilerplate (`ScalekitClient` setup, env loading, variable declarations). They are continuation snippets that rely on the client already defined in the `list_scoped_tools` discovery block above. Do not flag these as lacking self-contained initialization in future reviews.
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 623
File: src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx:143-237
Timestamp: 2026-04-22T04:05:02.920Z
Learning: In `src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx`, the MCP tool calling SDK examples (`list_scoped_tools` / `execute_tool`, under the "MCP tool calling" section) only include Node.js and Python tabs because Go and Java SDK support for this functionality is not yet available. Do not require or enforce Go and Java tabs in `<Tabs syncKey="tech-stack">` blocks for MCP tool calling in bring-your-own-connector docs until those SDKs support the feature.
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 529
File: src/content/docs/agent-auth/mcp/tool-access-via-mcp.mdx:188-190
Timestamp: 2026-03-25T10:15:02.544Z
Learning: In scalekit-inc/developer-docs, the Aside note in `src/content/docs/agent-auth/mcp/tool-access-via-mcp.mdx` warning that ChatGPT's beta MCP connector "may not work correctly" and "does not fully implement the MCP specification" is intentional. Real-world developers have reported re-auth loops and inconsistent streamable HTTP behaviour with ChatGPT compared to Claude, even though OpenAI's marketing describes it as "full MCP support". Do not flag or suggest removing this compatibility warning in future reviews.
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 0
File: :0-0
Timestamp: 2026-03-13T04:24:59.653Z
Learning: In scalekit-inc/developer-docs, for PRs focused on tooling and templatizing (e.g., extracting usage sections into reusable MDX templates and updating sync scripts), review comments about .mdx file content quality (casing, unused imports, import consolidation, endpoint descriptions, etc.) are considered out of scope and should be resolved without blocking the PR.
Learnt from: CR
Repo: scalekit-inc/developer-docs PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-20T11:29:40.242Z
Learning: Product-based documentation (MCP Auth, Agent Auth, Full Stack Auth, Modular SCIM, Modular SSO) must follow a journey-focused approach representing a developer's journey toward implementing authentication
Learnt from: CR
Repo: scalekit-inc/developer-docs PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-04-20T11:30:52.410Z
Learning: Product-based documentation (MCP Auth, Agent Auth, Full Stack Auth, Modular SCIM, Modular SSO) MUST follow a journey-focused approach. Each product represents a developer's journey toward implementing authentication in their projects
Learnt from: dhaneshbs
Repo: scalekit-inc/developer-docs PR: 487
File: src/content/docs/agent-auth/connections.mdx:0-0
Timestamp: 2026-03-12T05:02:13.454Z
Learning: In `src/content/docs/agent-auth/connections.mdx` (and Agent Auth docs generally), custom authentication (username/password/bearer-token flows) is intentionally out of scope for the current Agent Auth release. Do not flag the absence of custom authentication connection type documentation in Agent Auth connection-type sections.
Learnt from: dhaneshbs
Repo: scalekit-inc/developer-docs PR: 487
File: src/content/docs/agent-auth/connections.mdx:0-0
Timestamp: 2026-03-12T05:02:13.454Z
Learning: In `src/content/docs/agent-auth/connections.mdx` (and Agent Auth docs in general), custom authentication (username/password/bearer-token flows) is intentionally out of scope for the current Agent Auth release. Do not flag the absence of custom authentication documentation in Agent Auth connection-type sections.
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/googlesheets.mdx:95-141
Timestamp: 2026-02-26T07:22:55.583Z
Learning: For MDX files under src/content/docs/reference/agent-connectors/, the parameter tables (showing tool properties) are auto-generated from JSON API responses by scripts/sync-agent-connectors.js. Any table format corrections must be made in the generation script, not by manually editing the generated MDX files. The script should be updated to output the required "Name | Type | Required | Description" four-column table format per coding guidelines.
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 455
File: src/content/docs/reference/agent-connectors/asana.mdx:94-173
Timestamp: 2026-03-03T13:35:56.400Z
Learning: For Agent Connectors documentation (src/content/docs/reference/agent-connectors/**/*.mdx), currently only Python SDK support is available for Agent Actions/Agent Connectors. Do not require or enforce the multi-language SDK code examples (Node.js, Python, Go, Java) guideline for these connector docs until SDK support is ready in other languages. The Node.js, Go, and Java examples can be added once the respective SDKs support Agent Actions features.
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/googlemeet.mdx:1-87
Timestamp: 2026-02-26T07:20:46.903Z
Learning: For auto-generated agent connector documentation pages in src/content/docs/reference/agent-connectors/, the "what's next" signal requirement (next: frontmatter link, <LinkCard>, or concluding paragraph) does not apply. These are reference pages generated by scripts/sync-agent-connectors.js and serve as lookup resources rather than sequential guides.
📚 Learning: 2026-04-20T17:03:02.786Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 619
File: src/components/templates/agent-connectors/_usage-posthogmcp.mdx:82-82
Timestamp: 2026-04-20T17:03:02.786Z
Learning: In `src/components/templates/agent-connectors/_usage-posthogmcp.mdx`, the trailing `## Scalekit Tools` heading is intentionally omitted. The parent connector page (`src/content/docs/agentkit/connectors/posthogmcp.mdx`) renders the tool list separately via the `ToolList` component and the imported `tools` dataset, so the structural anchor heading used by other `_usage-*.mdx` templates is not needed here. Do not flag the missing `## Scalekit Tools` heading in this file.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-04-22T09:58:57.649Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 623
File: src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx:197-227
Timestamp: 2026-04-22T09:58:57.649Z
Learning: In `src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx`, the `execute_tool` code examples (Node.js and Python) under the "MCP tool calling" section intentionally omit client initialization boilerplate (`ScalekitClient` setup, env loading, variable declarations). They are continuation snippets that rely on the client already defined in the `list_scoped_tools` discovery block above. Do not flag these as lacking self-contained initialization in future reviews.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-04-13T10:43:05.628Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 590
File: src/components/templates/agent-connectors/_usage-databricks.mdx:83-83
Timestamp: 2026-04-13T10:43:05.628Z
Learning: In `src/components/templates/agent-connectors/_usage-*.mdx` files, the trailing `## Scalekit Tools` heading at the end of every usage template is intentional and consistent across all 42+ connector usage templates. It acts as a structural anchor/separator that the parent connector reference page uses to append the tool-list section beneath the proxy API examples. Do not flag this heading as empty or duplicate in future reviews of these template files.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-04-20T11:29:40.242Z
Learnt from: CR
Repo: scalekit-inc/developer-docs PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-20T11:29:40.242Z
Learning: Applies to src/content/docs/agentkit/**/*.{md,mdx} : Agentkit code examples live in the external repo **scalekit-developers/agent-auth-examples** organized as `javascript/frameworks/<framework>` and `python/frameworks/<framework>`; verify docs snippets match current implementations in that repo
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-02-26T07:21:37.207Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/googlesheets.mdx:89-131
Timestamp: 2026-02-26T07:21:37.207Z
Learning: In src/content/docs/reference/agent-connectors/** MDX files, tool headings (e.g., `googlesheets_create_spreadsheet`, `googlesheets_get_values`) intentionally use H2 (##) instead of H3 to ensure they appear in the table of contents for easier navigation. This is a deliberate UX choice for agent connector reference pages and should not be flagged as a hierarchy issue.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-03-13T04:24:59.653Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 0
File: :0-0
Timestamp: 2026-03-13T04:24:59.653Z
Learning: In scalekit-inc/developer-docs, for PRs focused on tooling and templatizing (e.g., extracting usage sections into reusable MDX templates and updating sync scripts), review comments about .mdx file content quality (casing, unused imports, import consolidation, endpoint descriptions, etc.) are considered out of scope and should be resolved without blocking the PR.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-04-22T04:05:02.920Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 623
File: src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx:143-237
Timestamp: 2026-04-22T04:05:02.920Z
Learning: In `src/content/docs/agentkit/bring-your-own-connector/using-tool-proxy.mdx`, the MCP tool calling SDK examples (`list_scoped_tools` / `execute_tool`, under the "MCP tool calling" section) only include Node.js and Python tabs because Go and Java SDK support for this functionality is not yet available. Do not require or enforce Go and Java tabs in `<Tabs syncKey="tech-stack">` blocks for MCP tool calling in bring-your-own-connector docs until those SDKs support the feature.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-02-26T07:22:55.583Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/googlesheets.mdx:95-141
Timestamp: 2026-02-26T07:22:55.583Z
Learning: For MDX files under src/content/docs/reference/agent-connectors/, the parameter tables (showing tool properties) are auto-generated from JSON API responses by scripts/sync-agent-connectors.js. Any table format corrections must be made in the generation script, not by manually editing the generated MDX files. The script should be updated to output the required "Name | Type | Required | Description" four-column table format per coding guidelines.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-03-13T03:51:44.897Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 489
File: src/content/docs/reference/agent-connectors/attio.mdx:24-24
Timestamp: 2026-03-13T03:51:44.897Z
Learning: For any agent connector documentation files located in src/content/docs/reference/agent-connectors/, use CDN URLs for connector logos with the host `https://cdn.scalekit.com/sk-connect/assets/provider-icons/` (e.g., `https://cdn.scalekit.com/sk-connect/assets/provider-icons/attio.svg`). The correct host is `cdn.scalekit.com`, NOT `cdn.scalekit.cloud`. Do not flag or change image src attributes that use `cdn.scalekit.com` for provider icons in this directory.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-02-26T07:23:27.672Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 448
File: src/content/docs/reference/agent-connectors/microsoftword.mdx:3-3
Timestamp: 2026-02-26T07:23:27.672Z
Learning: For MDX files under src/content/docs/reference/agent-connectors/, do not enforce the 160-character description limit. These files are auto-generated from API payloads via scripts/sync-agent-connectors.js and may have longer descriptions from the source data.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-03-31T16:14:24.575Z
Learnt from: CR
Repo: scalekit-inc/developer-docs PR: 0
File: public/AGENTS.md:0-0
Timestamp: 2026-03-31T16:14:24.575Z
Learning: Use Scalekit official plugin for AI coding agents (Claude Code, GitHub Copilot, Codex, or Skills CLI/Windsurf/Cline) to reduce hallucinations and improve code generation accuracy
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-04-20T11:29:40.242Z
Learnt from: CR
Repo: scalekit-inc/developer-docs PR: 0
File: CLAUDE.md:0-0
Timestamp: 2026-04-20T11:29:40.242Z
Learning: Applies to **/*.{md,mdx} : Use exact SDK variable names: Node.js: `scalekit`, Python: `scalekit_client`, Go: `scalekitClient`, Java: `scalekitClient`
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-03-09T15:06:49.617Z
Learnt from: hrishikesh-p
Repo: scalekit-inc/developer-docs PR: 473
File: src/content/docs/agent-auth/tools/execute.mdx:34-76
Timestamp: 2026-03-09T15:06:49.617Z
Learning: In src/content/docs/agent-auth/tools/**/*.mdx (Agent Auth tool execution docs, e.g., execute.mdx, authorize.mdx), only Python and Node.js SDK support is currently available for Agent Auth tool execution. Do not require or enforce Go and Java tabs in Tabs syncKey="tech-stack" blocks for these files until the Go and Java SDKs support Agent Auth features. Add Go and Java TabItems once those SDKs are ready.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-01-30T18:18:50.883Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 415
File: src/content/docs/authenticate/fsa/multiapp/manage-apps.mdx:31-49
Timestamp: 2026-01-30T18:18:50.883Z
Learning: In all Scalekit documentation files (MDX), treat the terms 'Applications', 'Single Page Application (SPA)', 'Native Application', and 'Web Application' as proper nouns and preserve their capitalization in headings and body text. Ensure these terms remain capitalized even when used in sentence case or within prose.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-02-04T12:47:16.544Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 412
File: src/content/docs/dev-kit/tools/scalekit-dryrun.mdx:1-23
Timestamp: 2026-02-04T12:47:16.544Z
Learning: In scalekit-inc/developer-docs, the MDX frontmatter field order is required only when the sidebar configuration points to a directory (for auto-generation). If the sidebar.config.ts references a specific file path, the order field is not required. Apply this check to all MDX files under src/content/docs: if a file contributes to an auto-generated sidebar (directory path), ensure order is present; if it’s linked to a concrete file, order can be omitted. Use sidebar.config.ts to determine whether a given MDX file falls under directory-based vs file-specific sidebar references.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-02-25T08:57:12.201Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 444
File: src/content/docs/agent-auth/quickstart.mdx:2-10
Timestamp: 2026-02-25T08:57:12.201Z
Learning: In Scalekit developer-docs (Astro Starlight), do not auto-suggest adding tableOfContents in frontmatter unless the user explicitly overrides the default behavior. The default enables tableOfContents with minHeadingLevel 2 and maxHeadingLevel 3. Only set tableOfContents when you want to customize heading levels or disable it entirely; otherwise omit it for other docs.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-02-25T13:04:27.491Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 444
File: src/content/docs/agent-auth/start-agent-auth-coding-agents.mdx:9-17
Timestamp: 2026-02-25T13:04:27.491Z
Learning: Allow page-level CSS overrides in MDX frontmatter (head: style) for readability and engagement, even if it customizes typography beyond defaults. This applies to per-page UX decisions, including heading sizes and style tweaks, but keep overrides purposeful, accessible, and within the repository's design guidelines. Use these overrides sparingly and document the rationale for maintainability.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-03-05T11:29:08.125Z
Learnt from: AkshayParihar33
Repo: scalekit-inc/developer-docs PR: 463
File: src/content/docs/agent-auth/providers.mdx:35-73
Timestamp: 2026-03-05T11:29:08.125Z
Learning: In src/content/docs/agent-auth/providers.mdx, the Card components intentionally use icon=" " (a space) to render consistent colored boxes since some Starlight icon names resolve to icons and others do not. Do not flag icon=" " as a placeholder issue for this file; treat this as a deliberate UX choice specific to this MDX page and avoid raising a placeholder-icon warning here.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-03-09T07:27:56.794Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 469
File: src/content/docs/guides/integrations/scim-integrations/azure-scim.mdx:95-107
Timestamp: 2026-03-09T07:27:56.794Z
Learning: Do not enforce the 3-space indentation rule for Steps component content as a hard style rule in MDX files under src/content/docs/**/*.mdx. Only flag/rectify it if it causes visible rendering problems in the UI. Otherwise, allow current formatting; apply this rule only when rendering issues are observed and document any fixes.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-03-09T07:32:38.426Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 467
File: src/content/docs/sso/guides/sso-user-attributes.mdx:108-148
Timestamp: 2026-03-09T07:32:38.426Z
Learning: In MDX code samples under src/content/docs (and similar conceptual snippets in scalekit-inc/developer-docs), when an example's sole purpose is to show how to access a specific value (e.g., reading JWT claims after token validation), omit error/non-happy-path handling to keep the snippet focused. Do not flag the absence of error paths in narrowly scoped conceptual snippets.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-03-17T16:01:50.487Z
Learnt from: dhaneshbs
Repo: scalekit-inc/developer-docs PR: 506
File: src/content/docs/authenticate/fsa/quickstart.mdx:851-853
Timestamp: 2026-03-17T16:01:50.487Z
Learning: In the Scalekit Python SDK docs, clarify that LogoutUrlOptions is not exported from the top-level scalekit package __init__.py. The correct import path in code samples or reviews is: from scalekit.common.scalekit import LogoutUrlOptions. Do not flag this import path as incorrect in documentation or code reviews; ensure examples reflect the proper import path to avoid confusion for users.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-02-25T03:34:41.147Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 444
File: src/content/docs/agent-auth/start-agent-auth-coding-agents.mdx:31-31
Timestamp: 2026-02-25T03:34:41.147Z
Learning: In MDX files, import { Code } from 'astrojs/starlight/components' only if the MDX content actually uses the <Code> component. If the file uses only fenced code blocks (```), the import is not required. Apply this guideline to all MDX files (e.g., src/content/docs/**/*.mdx) to avoid unnecessary imports and reduce bundle size.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
📚 Learning: 2026-02-25T18:41:00.639Z
Learnt from: saif-at-scalekit
Repo: scalekit-inc/developer-docs PR: 446
File: src/content/docs/authenticate/m2m/api-auth-quickstart.mdx:78-78
Timestamp: 2026-02-25T18:41:00.639Z
Learning: Preserve full URLs inside code comments in MDX code blocks (bash/python/js) when the URLs are part of copyable examples. Do not flag these in code examples. Use relative paths in prose and hyperlinks within MDX; only enforce relative paths for markdown prose links, not for URLs inside code comments.
Applied to files:
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx
🔇 Additional comments (1)
src/content/docs/agentkit/tools/scalekit-optimized-tools.mdx (1)
214-215: Good update to useconnection_namesin framework adapters.This aligns the adapter examples with the connector-name based filtering shown elsewhere on the page.
Also applies to: 229-230
…eview/actions-custom-mcp-provider-tools
…676) * chore: improve CodeRabbit config to reduce noise and add auto-fixes Audited CodeRabbit comments across the last 30 merged PRs (#623-#673) and identified recurring noisy, incorrect, or low-value feedback patterns. Changes: - Add tone_instructions to reduce verbose duplicate explanations - Add path_filters to exclude generated connector reference MDX, lock files - Enable markdownlint, languagetool, actionlint, shellcheck tools for deterministic linting instead of AI guessing - Add finishing_touches custom recipes to auto-fix missing frontmatter and hardcoded absolute docs URLs (caused ~40% of all change requests) - Add knowledge_base pointing to CLAUDE.md, CONTRIBUTING.md, AGENTS.md so reviews are grounded in repo standards - Add ignore_title_keywords to skip WIP PRs - Add path_instructions for .github/workflows/ to stop noisy force-push and concurrency group suggestions - Add path_instructions for src/data/agent-connectors/ to stop refactoring suggestions on data definition files - Add path_instructions for connector setup templates to relax the 4-language SDK tab requirement where it doesn't apply - Exempt API identifiers from sentence-case heading checks * fix: trim tone_instructions to fit 250-char limit * fix: remove TYPOS from languagetool enabled_categories (always disabled)
2 participants
Summary
Introduce MCP connectors as a second type of custom provider alongside REST API providers across the bring-your-own-connector documentation section.
list_scoped_toolsandexecute_toolfor MCP tool callingPreview
https://deploy-preview-623--scalekit-starlight.netlify.app/agentkit/bring-your-own-connector/overview/
Summary by CodeRabbit
Documentation
Chores