-
Notifications
You must be signed in to change notification settings - Fork 366
Add Kreuzberg document intelligence MCP shared workflow #28392
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
+88
−0
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,88 @@ | ||
| --- | ||
| mcp-servers: | ||
| kreuzberg: | ||
| container: "ghcr.io/kreuzberg-dev/kreuzberg" | ||
| version: "latest" | ||
| entrypointArgs: | ||
| - "mcp" | ||
| mounts: | ||
| - ${GITHUB_WORKSPACE}:${GITHUB_WORKSPACE}:ro | ||
| allowed: | ||
| # Document extraction tools (read-only) | ||
| - "extract_file" | ||
| - "extract_bytes" | ||
| - "batch_extract_files" | ||
| # Format discovery tools (read-only) | ||
| - "detect_mime_type" | ||
| - "list_formats" | ||
| - "get_version" | ||
| # Text processing tools (read-only) | ||
| - "embed_text" | ||
| - "chunk_text" | ||
| # Cache inspection tools (read-only) | ||
| - "cache_stats" | ||
| - "cache_manifest" | ||
| # Excluded write/mutating operations: | ||
| # - "cache_clear" # Evicts all cached results | ||
| # - "cache_warm" # Pre-downloads embedding models | ||
| # Excluded feature-flag-gated operations: | ||
| # - "extract_structured" # Requires liter-llm feature flag at build time | ||
| --- | ||
| <!-- | ||
| ## Kreuzberg MCP Server | ||
|
|
||
| Kreuzberg is a polyglot document intelligence engine. The MCP server exposes its | ||
| full extraction engine as 13 discoverable tools, communicating over stdin/stdout | ||
| with JSON-RPC 2.0. It supports 97+ file formats including PDF, DOCX, PPTX, | ||
| images (with Tesseract OCR), and legacy Office formats (with LibreOffice in the | ||
| full image). | ||
|
|
||
| Documentation: https://docs.kreuzberg.dev/guides/docker/ | ||
| MCP integration guide: https://docs.kreuzberg.dev/guides/mcp-integration/ | ||
| GitHub: https://github.com/kreuzberg-dev/kreuzberg | ||
|
|
||
| ### Container images | ||
|
|
||
| Two images are available (both on `ghcr.io/kreuzberg-dev/kreuzberg`): | ||
| - **Core** (~1.0–1.3 GB): Modern formats, Tesseract OCR (12 languages) | ||
| - **Full** (~1.5–2.1 GB): Adds LibreOffice for legacy `.doc`/`.ppt` files | ||
| Use tag `full` or `latest-full` to select the full image. | ||
|
|
||
| ### Required secrets | ||
|
|
||
| None — no API token is required. | ||
|
|
||
| ### Available tools (read-only) | ||
|
|
||
| | Tool | Params | Description | | ||
| |---|---|---| | ||
| | `extract_file` | `path` | Extract text and metadata from a local file | | ||
| | `extract_bytes` | `data` (base64) | Extract from base64-encoded file content | | ||
| | `batch_extract_files` | `paths` | Extract multiple files in one call | | ||
| | `detect_mime_type` | `path` | Identify a file's MIME type | | ||
| | `list_formats` | — | List all supported file formats | | ||
| | `get_version` | — | Return the library version string | | ||
| | `embed_text` | `texts` | Generate embedding vectors for text chunks | | ||
| | `chunk_text` | `text` | Split text into overlapping chunks | | ||
| | `cache_stats` | — | Report how much content is cached | | ||
| | `cache_manifest` | — | Return model checksums | | ||
|
|
||
| ### Excluded tools | ||
|
|
||
| - `cache_clear` — Evicts all cached results (write operation) | ||
| - `cache_warm` — Pre-downloads embedding models (write operation) | ||
| - `extract_structured` — Requires the `liter-llm` build-time feature flag | ||
|
|
||
| ### Workspace access | ||
|
|
||
| The workspace is mounted read-only at the same path it exists on the host, | ||
| so `extract_file` and `batch_extract_files` can reference files using their | ||
| absolute workspace paths (e.g. `${{ github.workspace }}/document.pdf`). | ||
|
|
||
| ### Usage in workflows | ||
|
|
||
| ```yaml | ||
| imports: | ||
| - shared/mcp/kreuzberg.md | ||
| ``` | ||
| --> | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The markdown table under "Available tools (read-only)" uses double leading pipes (
|| ...) on each row, which is not valid table syntax and makes the table hard to read/parse in raw form. Use standard single-pipe table rows (e.g.,| Tool | Params | Description |,|---|---|---|, etc.).