Open behavioral litmus for MCP servers — grades A–F across tool-output injection, egress, sensitive-data, and adversarial-input, with reproducible, content-addressed evidence. Tools: run_litmus, verify_attestation.
4
157
7
Apache 2.0
Why this server?
Integrated as part of the contribution workflow to ensure code quality before submission.
Structural graph map of any codebase. Scans entities, relationships, and feature flows across 13 languages so LLMs navigate by structure instead of
reading everything.
6
14
MIT
Why this server?
Installs pre-commit hooks for license validation checks to ensure compliance before commits are made.
A unified developer toolkit for AI-assisted workflows. Task timing, doc drift detection, env validation, secret scanning, port conflict resolution, AI context generation, and license auditing — one MCP server, one install.
7
3
MIT
Why this server?
Integrates with pre-commit hooks to block insecure code before it reaches the repository.
Security MCP server with 300+ rules for AI-generated code. Scans Next.js, Supabase, Clerk, Stripe, Prisma, Hono, GraphQL and 20+ modules. Zero config, runs locally.
39
300
5
Apache 2.0
Why this server?
Provides a pre-commit hook to automatically scan staged changes for security issues before committing.
MCP server that enables AI coding tools to scan projects for security vulnerabilities, secret leaks, and compliance issues, generating Korean-language audit reports.
