CodeQL MCP Server
by JordyZomer
This project runs a Model Context Protocol (MCP) server that wraps the CodeQL query server. It enables tools like Cursor or AI agents to interact with CodeQL through structured commands and doc search.
Last updated: N/A
What is CodeQL MCP Server?
The CodeQL MCP Server is a server that wraps the CodeQL query server using the Model Context Protocol (MCP). This allows tools like Cursor and AI agents to interact with CodeQL in a structured way.
How to use CodeQL MCP Server?
- Install the requirements using
uv pip install -r requirements.txtorpip install fastmcp httpx. 2. Run the server usinguv run mcp run server.py -t sse. 3. Configure your Cursor config file (.cusor/config.json) to point to the server URL (http://localhost:8000/sse). 4. Ensure you have a codeql binary in your $PATH or hardcode its path in codeqlclient.py. Specify query locations, query write locations and database paths in your prompts.
Key features of CodeQL MCP Server
Register CodeQL databases
Run full queries or quick-evaluate a symbol
Decode
.bqrsfiles into JSONLocate predicate/class symbol positions
Use cases of CodeQL MCP Server
Integrating CodeQL analysis into AI-powered code editors
Enabling natural language interaction with CodeQL
Automating CodeQL queries through AI agents
Providing structured access to CodeQL functionality for various tools
FAQ from CodeQL MCP Server
What is MCP?
What is MCP?
Model Context Protocol
What is CodeQL?
What is CodeQL?
A semantic code analysis engine.
Why use this server?
Why use this server?
To enable tools like Cursor or AI agents to interact with CodeQL through structured commands and doc search.
What are the requirements?
What are the requirements?
fastmcp, httpx, and a codeql binary in your $PATH.
How do I configure Cursor?
How do I configure Cursor?
Make sure your .cusor/config.json contains the server URL (http://localhost:8000/sse).