Allows cloning and processing of local git repositories, extracting code context from different branches and files for semantic search.
Code Context MCP Server
A Model Context Protocol (MCP) server for providing code context from local git repositories. This server allows you to:
Clone git repositories locally
Process branches and files
Generate embeddings for code chunks
Perform semantic search over code
Features
Uses local git repositories instead of GitHub API
Stores data in SQLite database
Splits code into semantic chunks
Generates embeddings for code chunks using Ollama
Provides semantic search over code
Related MCP server: Git MCP
Prerequisites
Node.js (v16+)
Git
Ollama with an embedding model
Installation
Configuration
Set the following environment variables:
DATA_DIR: Directory for SQLite database (default: '~/.codeContextMcp/data')REPO_CACHE_DIR: Directory for cloned repositories (default: '~/.codeContextMcp/repos')
Using Ollama
For faster and more powerful embeddings, you can use Ollama:
Usage
Using with Claude Desktop
Add the following configuration to your Claude Desktop configuration file (claude_desktop_config.json):
Tools
The server provides the following tool:
queryRepo
Clones a repository, processes code, and performs semantic search:
The branch parameter is optional. If not provided, the tool will automatically use the repository's default branch.
The keywords parameter is optional. If provided, the results will be filtered to only include chunks that contain at least one of the specified keywords (case-insensitive matching).
The filePatterns and excludePatterns parameters are optional. They allow you to filter which files are processed and searched using glob patterns (e.g., **/*.ts for all TypeScript files).
Database Schema
The server uses SQLite with the following schema:
repository: Stores information about repositoriesbranch: Stores information about branchesfile: Stores information about filesbranch_file_association: Associates files with branchesfile_chunk: Stores code chunks and their embeddings
Debugging
MAC Mx Series - ARM Architecture Issues
When installing better-sqlite3 on Mac M-series chips (ARM architecture), if you encounter errors like "mach-o file, but is an incompatible architecture (have 'x86_64', need 'arm64e' or 'arm64')", you need to ensure the binary matches your architecture. Here's how to resolve this issue:
If you're using Rosetta, make sure your entire environment is consistent. Your error shows x86_64 binaries being built but your system needs arm64. For persistent configuration, add to your .zshrc or .bashrc:
Testing Ollama Embeddings
curl http://localhost:11434/api/embed -d '{"model":"unclemusclez/jina-embeddings-v2-base-code","input":"Llamas are members of the camelid family"}' curl http://127.0.01:11434/api/embed -d '{"model":"unclemusclez/jina-embeddings-v2-base-code","input":"Llamas are members of the camelid family"}' curl http://[::1]:11434/api/embed -d '{"model":"unclemusclez/jina-embeddings-v2-base-code","input":"Llamas are members of the camelid family"}'
License
MIT