Skip to content
Back to search

codeql-mcp

This project runs a Model Context Protocol (MCP) server that wraps the CodeQL query server. It enables tools like [Cursor](https://cursor.sh/) or AI agents to interact with CodeQL through structured commands.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/jordyzomer--codeql-mcp/badge.svg)](/listings/jordyzomer--codeql-mcp)

HTML

<a href="/listings/jordyzomer--codeql-mcp"><img src="/api/listings/jordyzomer--codeql-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 61 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # CodeQL MCP Server
  2. This project runs a Model Context Protocol (MCP) server that wraps the CodeQL query server. It enables tools like [Cursor](https://cursor.sh/) or AI agents to interact with CodeQL through structured commands and doc search.
  3. ---
  4. ## Features
  5. - ✅ Register CodeQL databases
  6. - ✅ Run full queries or quick-evaluate a symbol
  7. - ✅ Decode `.bqrs` files into JSON
  8. - ✅ Locate predicate/class symbol positions
  9. ---
  10. ## File Structure
  11. | File | Purpose |
  12. |-------------------|-----------------------------------------------------|
  13. | `server.py` | Main FastMCP server exposing CodeQL tools |
  14. | `codeqlclient.py` | CodeQLQueryServer implementation (JSON-RPC handler) |
  15. ---
  16. ## Requirements
  17. Install with [`uv`](https://github.com/astral-sh/uv):
  18. ```bash
  19. uv pip install -r requirements.txt
  20. ```
  21. or with `pip`:
  22. ```bash
  23. pip install fastmcp httpx
  24. ```
  25. ## Running the MCP Server
  26. ```bash
  27. uv run mcp run server.py -t sse
  28. ```
  29. - Starts the server at http://localhost:8000/sse
  30. - Required for Cursor or AI agent use
  31. ## Cursor Config
  32. Make sure your `.cusor/config.json` contains:
  33. ```
  34. {
  35. "mcpServers": {
  36. "CodeQL": {
  37. "url": "http://localhost:8000/sse"
  38. }
  39. }
  40. }
  41. ```
  42. ## Notes
  43. - Tools like Cursor will invoke these commands directly via natural language.
  44. - You must have a codeql binary in your $PATH, or hardcode its path in codeqlclient.py.
  45. - You should probably specify query locations, query write locations and database paths in your prompts.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.