code-intel-mcp
MCP server that gives AI agents deep code understanding across multiple git repositories, combining git lifecycle management, Zoekt-based trigram code search, and cross-repo dependency analysis.
README
code-intel-mcp
MCP server that gives AI agents deep code understanding across multiple git repositories. Combines git lifecycle management, Zoekt-based trigram code search, and cross-repo dependency analysis.
Quick Start (macOS)
Prerequisites
Install uv (Python package runner):
brew install uv
1. Setup (one time)
uvx code-intel-mcp setup --zoekt-url "https://github.com/arunveersingh/code-intel-mcp/releases/download/v0.1.0"
This creates ~/.code-intel-mcp/ directories and downloads the Zoekt search engine binaries.
2. Add to your MCP client
Kiro — add to ~/.kiro/settings/mcp.json inside "mcpServers":
"code-intel-mcp": {
"command": "uvx",
"args": ["code-intel-mcp", "serve"],
"env": {
"GITLAB_URL": "https://your-gitlab.com",
"GITLAB_TOKEN": "<your-personal-access-token>"
},
"disabled": false,
"autoApprove": []
}
Claude Desktop — add to ~/Library/Application Support/Claude/claude_desktop_config.json inside "mcpServers":
"code-intel-mcp": {
"command": "uvx",
"args": ["code-intel-mcp", "serve"],
"env": {
"GITLAB_URL": "https://your-gitlab.com",
"GITLAB_TOKEN": "<your-personal-access-token>"
}
}
3. Done
Restart your MCP client. Your AI agent now has access to 15 tools for code intelligence.
Features
- Git lifecycle — clone, pull, checkout, sync, and remove repositories
- GitLab integration — bulk-clone entire GitLab groups
- Code search — fast trigram-based search powered by Zoekt
- File browsing — read files, list directories, get repo overviews
- Dependency analysis — parse Maven, Gradle, and npm build configs
- Symbol references — word-boundary search across repos
Available Tools
| Tool | Description |
|---|---|
repo_add |
Clone and register a git repository |
repo_add_gitlab_group |
Bulk-clone all projects from a GitLab group |
repo_list |
List all managed repositories |
repo_info |
Detailed repo info (branches, tags, commits, size) |
repo_checkout |
Switch to a branch, tag, or commit SHA |
repo_pull |
Pull latest changes |
repo_sync_all |
Pull all managed repositories |
repo_remove |
Remove a repository and its index |
search_code |
Search code with language/file filters |
search_files |
Search for files by name pattern |
search_references |
Find symbol references across repos |
read_file |
Read file contents |
list_directory |
List directory contents |
get_repo_overview |
Repo summary (README, structure, build info) |
find_dependencies |
Analyze build config dependencies |
Environment Variables
| Variable | Required | Description |
|---|---|---|
GITLAB_URL |
For GitLab features | Base URL of your GitLab instance |
GITLAB_TOKEN |
For GitLab features | Personal access token with read_api scope |
How It Works
The server manages a local repository store at ~/.code-intel-mcp/:
~/.code-intel-mcp/
├── repos/ # Cloned git repositories
├── index/ # Zoekt search index
├── bin/ # Zoekt binaries (auto-installed)
└── config.json # Registry of managed repos
Every git mutation (clone, pull, checkout) automatically triggers Zoekt re-indexing, keeping search results current. The server auto-prepends ~/.code-intel-mcp/bin to PATH on startup, so no manual PATH configuration is needed.
Troubleshooting
spawn code-intel-mcp ENOENT — Use "command": "uvx" with "args": ["code-intel-mcp", "serve"], not "command": "code-intel-mcp".
Requires-Python >=3.11 — Use uvx instead of pip install. It handles Python versions automatically.
Zoekt binaries not found — Re-run setup: uvx code-intel-mcp setup --zoekt-url "https://github.com/arunveersingh/code-intel-mcp/releases/download/v0.1.0"
Development
git clone https://github.com/arunveersingh/code-intel-mcp.git
cd code-intel-mcp
python3 -m venv .venv && source .venv/bin/activate
pip install hatchling && python3 -m hatchling build -t wheel
pip install dist/*.whl && pip install pytest pytest-asyncio hypothesis
pytest
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.