A Model Context Protocol (MCP) server that provides AI-enhanced code search capabilities using Sourcegraph.
- Overview
- Features
- Prerequisites
- Installation
- Configuration
- Usage with AI Tools
- MCP Tools
- Development
This MCP server integrates with Sourcegraph, a universal code search platform that enables searching across multiple repositories and codebases. It provides powerful search capabilities with advanced query syntax, making it ideal for AI assistants that need to find and understand code patterns across large codebases.
- Code Search: Search across codebases using Sourcegraph's powerful query language
- Advanced Query Language: Support for regex patterns, file filters, language filters, and boolean operators
- Repository Discovery: Find repositories by name and explore their structure
- Content Fetching: Browse repository files and directories
- AI Integration: Designed for LLM integration with guided search prompts
- Sourcegraph Instance: Access to a Sourcegraph instance (either sourcegraph.com or self-hosted)
- Python 3.10+: Required for running the MCP server
- UV (optional): Modern Python package manager for easier dependency management
# Install dependencies
uv sync
# Run the server
uv run python -m src.main
# Create virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install package
pip install -e .
# Run the server
python -m src.main
# Build the image
docker build -t sourcegraph-mcp .
# Run the container with default ports
docker run -p 8000:8000 -p 8080:8080 \
-e SRC_ENDPOINT=https://sourcegraph.com \
-e SRC_ACCESS_TOKEN=your-token \
sourcegraph-mcp
# Or run with custom ports
docker run -p 9000:9000 -p 9080:9080 \
-e SRC_ENDPOINT=https://sourcegraph.com \
-e SRC_ACCESS_TOKEN=your-token \
-e MCP_SSE_PORT=9000 \
-e MCP_STREAMABLE_HTTP_PORT=9080 \
sourcegraph-mcp
SRC_ENDPOINT
: Sourcegraph instance URL (e.g., https://sourcegraph.com)
SRC_ACCESS_TOKEN
: Authentication token for private Sourcegraph instancesMCP_SSE_PORT
: SSE server port (default: 8000)MCP_STREAMABLE_HTTP_PORT
: HTTP server port (default: 8080)
After running the MCP server, add the following to your .cursor/mcp.json
file:
{
"mcpServers": {
"sourcegraph": {
"url": "http://localhost:8080/sourcegraph/mcp/"
}
}
}
This server provides three powerful tools for AI assistants:
Search across codebases using Sourcegraph's advanced query syntax with support for regex, language filters, and boolean operators.
Generate a context-aware guide for constructing effective search queries based on your specific objective.
Retrieve file contents or explore directory structures from repositories.
# Check code style
uv run ruff check src/
# Format code
uv run ruff format src/