Skip to content
@dotsetlabs

Dotset Labs

Security for the AI Era

Dotset Labs

Security tools for AI-assisted development.

Website Documentation License


Our Products

We build security tools that help developers work safely with AI assistants. From drift detection to config scanning to runtime firewalling, our products provide visibility and control over MCP-powered workflows.

Layer Tool Purpose
DETECT Bellwether Structural drift detection for MCP servers
SCAN Hardpoint Rules File Backdoor detection in AI configs
CONTROL Overwatch AI Agent Firewall with tool shadowing detection

Bellwether

Structural Drift Detection for MCP Servers

Detect when your MCP server's tools, schemas, or descriptions change. The check command provides zero-LLM structural validation that catches breaking changes before they reach production. The optional explore command adds LLM-powered multi-persona behavioral testing and AGENTS.md documentation.

Website npm GitHub

# Initialize config and run structural drift detection
npx @dotsetlabs/bellwether init
bellwether check

# Save baseline and detect drift in CI/CD
bellwether baseline save
bellwether baseline compare --fail-on-drift

# Optional: LLM-powered behavioral exploration
bellwether explore

Features

Feature Description
Schema Validation Zero-LLM detection of tool additions, removals, schema changes, and renames
Security Analysis Detect SQL injection, XSS, path traversal, command injection, and SSRF vulnerabilities
Semantic Validation Auto-infer and validate semantic types (dates, URLs, emails, IDs)
Performance Monitoring Track response latency with confidence metrics and detect regressions
Multi-Persona Exploration Optional LLM testing from 4 perspectives: Technical Writer, Security Tester, QA Engineer, Novice User
CI/CD Integration Granular exit codes (0-5) for pipeline integration with --fail-on-drift
MCP Registry Search Discover and test servers from the MCP Registry

Commands

Core: checkexplorediscoverwatchinitvalidate-config

Baseline: baseline savebaseline comparebaseline showbaseline diffbaseline accept

Advanced: golden savegolden comparecontract generatecontract validateverify

Cloud: loginteamslinkprojectsuploadhistorydiffbadge

Auth: auth addauth removeauth statusauth clear

Output Formats

  • CONTRACT.md — Generated by check command with schema validation results
  • AGENTS.md — Generated by explore command with behavioral documentation
  • JSON / JUnit XML / SARIF — For CI/CD and GitHub Code Scanning integration

Cloud Platform

The open-source CLI works standalone. The optional cloud platform adds:

  • Baseline storage and version history
  • Team collaboration with role-based access
  • Webhook notifications
  • Verification badges

Hardpoint

The Rules File Backdoor Detector

Static security scanner for AI configuration files. Detects the Rules File Backdoor attack (24 CVEs in 2025) — where hidden malicious instructions lurk in .cursorrules, CLAUDE.md, and other AI config files.

GitHub

# Install
go install github.com/dotsetlabs/hardpoint/cmd/hardpoint@latest

# Scan AI config files
hardpoint scan

# Trust verified configs with hash verification
hardpoint trust CLAUDE.md

Detection Rules

Rule Severity Description
AI-008 Critical Semantic hijacking — hidden instructions in comments/structure
AI-005 Critical MCP command injection in server configurations
AI-004 Medium Base64 or otherwise encoded instructions
GIT-001–006 Critical–Medium Malicious hooks, credential exfiltration, suspicious remotes

AI Config Files Scanned

.cursorrulesCLAUDE.mdAGENTS.mdmcp.json.github/copilot-instructions.md.windsurfrules.aider*

Commands

scantrustverifyhook


Overwatch

The AI Agent Firewall

Runtime security proxy for MCP. Protects AI development environments by detecting tool impersonation attacks (CVE-2025-6514) and enforcing policy-based access control.

npm GitHub

# Install
npm install -g @dotsetlabs/overwatch

# Wrap any MCP server with security proxy
overwatch wrap npx @modelcontextprotocol/server-postgres

# Initialize configuration
overwatch init

Core Features

Feature Description
Tool Shadowing Detection Cryptographic verification — schema hashing, collision detection, mutation monitoring
Policy Engine Declarative YAML policies with allow/deny/prompt actions
Session Approvals Time-limited grants: once, 5 minutes, or session-based
Path-Based Rules Restrict filesystem access by glob patterns
Audit Logging Complete trail with JSON, CEF export for SIEM integration

Commands

wrapstartinitdoctorlogsstatssessionspolicies

Works With

Claude Desktop • Cursor • Any MCP-compatible AI agent


Trust & Security

Your data stays on your machine. Hardpoint and Overwatch are 100% local — no cloud, no telemetry, no account required. Bellwether's CLI works offline; the cloud platform is optional.

Tool Language License Cloud Required
Bellwether TypeScript MIT Optional
Hardpoint Go MIT No
Overwatch TypeScript MIT No

Links

Built for developers working with AI.

Washington, D.C.

Popular repositories Loading

  1. .github .github Public

  2. overwatch overwatch Public

    AI Agent Firewall for MCP. Detects tool shadowing attacks (CVE-2025-6514), enforces policies, and provides complete audit trails for AI coding assistant operations.

    TypeScript

  3. hardpoint hardpoint Public

    Detect Rules File Backdoor attacks in AI config files. Scans CLAUDE.md, .cursorrules, mcp.json for hidden prompt injection with 80+ obfuscation-resistant patterns.

    Go

  4. bellwether bellwether Public

    Open-source testing tool for Model Context Protocol (MCP) servers. Detect breaking schema changes before they reach production. Free deterministic validation with optional LLM-powered behavioral ex…

    TypeScript

Repositories

Showing 4 of 4 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…