Code Research MCP Server
Search and access programming resources from Stack Overflow, MDN, GitHub, npm, and PyPI.
Code Research MCP Server
A Model Context Protocol server that provides tools for searching and accessing programming resources across multiple platforms. This server integrates with popular developer platforms to help LLMs find relevant code examples, documentation, and packages.
Features
Integrated Platforms
- Stack Overflow - Programming Q&A
- MDN Web Docs - Web development documentation
- GitHub - Code and repository search
- npm - JavaScript package registry
- PyPI - Python package index
Tools
search_stackoverflow
Search Stack Overflow for programming questions and answers.
- Parameters:
query(required): Search query stringlimit(optional): Maximum results (1-10, default: 5)
- Returns: Formatted list of questions with scores, answer counts, and excerpts
- Results are cached for 1 hour
search_mdn
Search MDN Web Docs for web development documentation.
- Parameters:
query(required): Search query string
- Returns: Top 5 MDN documentation matches with summaries and links
- Results are cached for 1 hour
search_github
Search GitHub for both repositories and code examples.
- Parameters:
query(required): Search query stringlanguage(optional): Filter by programming languagelimit(optional): Maximum results per category (1-10, default: 5)
- Returns: Two sections:
- Top repositories sorted by stars
- Relevant code files with repository context
- Results are cached for 1 hour
search_npm
Search npm registry for JavaScript packages.
- Parameters:
query(required): Search query stringlimit(optional): Maximum results (1-10, default: 5)
- Returns: Package information including version, description, and download stats
- Results are cached for 1 hour
search_pypi
Search PyPI for Python packages.
- Parameters:
query(required): Search query string
- Returns: Detailed package information including version, author, and links
- Results are cached for 1 hour
search_all
Search all platforms simultaneously for comprehensive results.
- Parameters:
query(required): Search query stringlimit(optional): Maximum results per platform (1-5, default: 3)
- Returns: Combined results from all platforms:
- Stack Overflow questions and answers
- MDN documentation
- GitHub repositories and code
- npm packages
- PyPI packages
- Results are cached for 1 hour
- Note: Executes all searches in parallel for faster response
Requirements
- Node.js >= 20.11.0
- npm >= 10.0.0
- Optional: GitHub personal access token for higher API rate limits
Installation
Installing via Smithery
To install Code Research Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @nahmanmate/code-research-mcp-server --client claude
Manual Installation
- Clone the repository and install dependencies:
git clone https://github.com/nahmanmate/code-research-mcp-server.git
cd code-research-server
npm install
- Build the server:
npm run build
- Configure MCP Settings:
Add the server configuration to your MCP settings file:
- VSCode:
~/.vscode-server/data/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json - Claude Desktop:
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json
- MacOS:
{
"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.
Development
Running in Development Mode
For development with auto-rebuild on changes:
npm run watch
Error Handling
The server implements robust error handling:
- API-specific error messages for each platform
- Rate limit handling for GitHub API
- Graceful fallbacks for service unavailability
- Cached responses to reduce API load
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. Use the MCP Inspector for detailed request/response monitoring:
npm run inspector
The Inspector provides:
- Real-time request/response monitoring
- Tool execution tracing
- Error stack traces
- Performance metrics
Visit the provided URL in your browser to access the debugging interface.
Caching
Results are cached using node-cache:
- Default TTL: 1 hour
- Separate cache keys per query/limit combination
- Platform-specific caching strategies
- Memory-efficient storage
Contributing
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
License
AGPLv3
Related Servers
OrdiscanMCP v1
MCP server for interacting with the Ordiscan API to query Bitcoin ordinals and inscriptions. Requires an Ordiscan API key.
Brave Search
Integrates the Brave Search API for both web and local search capabilities. Requires a BRAVE_API_KEY.
Caltrain MCP Server
Provides real-time Caltrain schedule information using GTFS data.
Weather
Provides weather data using the US National Weather Service (NWS) API. Built with pure JavaScript ES Modules.
ChunkHound
A local-first semantic code search tool with vector and regex capabilities, designed for AI assistants.
Research Task
An AI-powered research assistant that can investigate any topic using an interactive configuration wizard.
SerpApi
Provides search capabilities and data retrieval from SerpAPI and YouTube for AI assistants.
Minima
Local RAG (on-premises) with MCP server.
Rememberizer Common Knowledge
Provides semantic search and retrieval for internal company knowledge bases, including documents and Slack discussions.
Search Stock News
Search for stock news using the Tavily API.