zoekt
MCP server for Zoekt
claude mcp add --transport stdio najva-ai-zoekt-mcp uvx zoekt-mcp \ --env MCP_SSE_PORT="Default: 8000 (SSE server port)" \ --env ZOEKT_API_URL="URL of your Zoekt instance" \ --env MCP_STREAMABLE_HTTP_PORT="Default: 8080 (HTTP server port)"
How to use
Zoekt MCP Server provides code search capabilities powered by a Zoekt-backed indexing engine. It exposes MCP tools that allow an AI assistant or client to perform full-text code searches across multiple repositories, discover repositories and their structure, and fetch file contents from indexed sources. The server is designed for integration with AI workflows, enabling context-aware search prompts and guided query construction through its built-in tools. To use it, configure a Zoekt instance URL via ZOEKT_API_URL and run the MCP server with UV as described in installation steps. The MCP tools include search for code queries, search_prompt_guide to generate effective search prompts tailored to a goal, and fetch_content to retrieve file content or directory listings from indexed repositories. These capabilities help AI agents locate relevant code patterns, understand repository layouts, and fetch exact snippets needed for analysis or response generation.
How to install
Prerequisites:
- A running Zoekt instance accessible via HTTP(S)
- Python 3.10+ installed
- Optional: UV for easier dependency management
Installation options:
Using UV (recommended):
- Install dependencies and run the server using UV:
# Install dependencies and run the server
uv sync
uv run python src/main.py
Using pip:
# Create and activate virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install the package in editable mode
pip install -e .
# Run the server
python src/main.py
Using Docker:
# Build the image
docker build -t zoekt-mcp .
# Run the container with default ports
docker run -p 8000:8000 -p 8080:8080 \
-e ZOEKT_API_URL=http://your-zoekt-instance \
zoekt-mcp
# Or run with custom ports
docker run -p 9000:9000 -p 9080:9080 \
-e ZOEKT_API_URL=http://your-zoekt-instance \
-e MCP_SSE_PORT=9000 \
-e MCP_STREAMABLE_HTTP_PORT=9080 \
zoekt-mcp
Prerequisites recap:
- A Zoekt endpoint reachable via ZOEKT_API_URL
- Python 3.10+ (and UV if using UV workflow)
- Optional: Docker installed if you prefer containerized deployment
Additional notes
Environment variables:
- ZOEKT_API_URL: URL to your Zoekt instance (e.g., http://localhost:8080)
- MCP_SSE_PORT: Port for Server-Sent Events endpoint (default 8000)
- MCP_STREAMABLE_HTTP_PORT: Port for HTTP content fetch endpoint (default 8080) Common issues:
- Ensure Zoekt is reachable from the MCP server (CORS, network access, and correct API path)
- If using Docker, map ports correctly and pass the Zoekt URL as an environment variable
- When using UV or pip, ensure dependencies are installed and Python path is correctly set
- Check that the MCP server is started with the correct working directory so it can locate src/main.py Configuration tip:
- Keep ZOEKT_API_URL secure and avoid exposing internal endpoints publicly without authentication if your deployment requires it.
Related MCP Servers
jupyter
🪐 🔧 Model Context Protocol (MCP) Server for Jupyter.
mcp -odoo
A Model Context Protocol (MCP) server that enables AI assistants to securely interact with Odoo ERP systems through standardized resources and tools for data retrieval and manipulation.
falcon
Connect AI agents to CrowdStrike Falcon for automated security analysis and threat hunting
beemcp
BeeMCP: an unofficial Model Context Protocol (MCP) server that connects your Bee wearable lifelogger to AI via the Model Context Protocol
MCP-MultiServer-Interoperable-Agent2Agent-LangGraph-AI-System
This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independently (via SSE or STDIO), offering modularity and cloud-deployable execut
Helios
An AI IDE secure coding MCP service