code-research

Code Research MCP Server provides a suite of tools to help LLMs find and access programming resources across multiple platforms. It integrates Stack Overflow, MDN Web Docs, GitHub, npm, and PyPI, offering search capabilities tailored for code-related questions, documentation, repositories, and packages. The server exposes tools such as search_stackoverflow, search_mdn, search_github, search_npm, search_pypi, and search_all. Each tool returns structured results optimized for quick consumption by an LLM, with results cached to improve response times and reduce external API load. The search_all tool runs parallel queries across platforms for a comprehensive overview, making it useful when you want a broad-spectrum set of results in one call.

Prerequisites:

• Node.js >= 20.11.0
• npm >= 10.0.0
• Optional: GitHub personal access token for higher API rate limits

Installation steps:

1. Install via Smithery (automatic deployment):

npx -y @smithery/cli install @nahmanmate/code-research-mcp-server --client claude

2. Manual installation from source:

# Clone the repository
git clone https://github.com/nahmanmate/code-research-mcp-server.git
cd code-research-server

# Install dependencies
npm install

3. Build the server:

npm run build

4. Configure MCP Settings: Add the server configuration to your MCP settings file. Example:

{
  "mcpServers": {
    "code-research": {
      "command": "node",
      "args": ["/absolute/path/to/code-research-mcp-server/build/index.js"],
      "env": {
        "GITHUB_TOKEN": "your_github_token"  // Optional: Prevents rate limiting
      },
      "disabled": false,
      "alwaysAllow": []
    }
  }
}

Note: Replace /absolute/path/to with the actual path where you cloned the repository.

Tips and notes:

• If you hit GitHub API rate limits, provide a GitHub token via GITHUB_TOKEN to increase quotas.
• Results are cached per platform for 1 hour to reduce API load; this improves performance for repeated queries.
• The server supports parallel execution for search_all to deliver faster comprehensive results.
• For development, you can run in watch/ inspector modes to auto-rebuild and debug: npm run watch and npm run inspector.
• Ensure your environment has network access to external APIs (Stack Overflow, MDN, GitHub, npm, PyPI) for accurate results.