A Model Context Protocol server
A Model Context Protocol server. The code research mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 9 defined tools rather than through you.
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.
Everything the assistant can do here goes through one of these:
Tools — The Tools tool exposed by this serversearch_stackoverflow — Search Stack Overflow for programming questions and answers. - Parameters: - query (required): Search query string - limit (optional): Maximumsearch_mdn — Search MDN Web Docs for web development documentation. - Parameters: - query (required): Search query string - Returns: Top 5 MDN documentationsearch_github — Search GitHub for both repositories and code examples. - Parameters: - query (required): Search query string - language (optional): Filter bysearch_npm — Search npm registry for JavaScript packages. - Parameters: - query (required): Search query string - limit (optional): Maximum results (1-10search_pypi — Search PyPI for Python packages. - Parameters: - query (required): Search query string - Returns: Detailed package information including versionsearch_all — Search all platforms simultaneously for comprehensive results. - Parameters: - query (required): Search query string - limit (optional): MaximumDebugging — Since MCP servers communicate over stdio, debugging can be challenging. Use the MCP Inspector for detailed request/response monitoring:Caching — Results are cached using node-cache: - Default TTL: 1 hour - Separate cache keys per query/limit combination - Platform-specific caching strategies -Installation goes through your MCP client rather than a global install: point it at @smithery/cli on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
You will need one environment variable: GITHUB_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Code Research's toolset — Tools, search_stackoverflow, search_mdn and 6 more — is a fair guide to whether it matches your workflow. It is maintained by nahmanmate; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Tools | The Tools tool exposed by this server. |
| search_stackoverflow | Search Stack Overflow for programming questions and answers. - Parameters: - query (required): Search query string - limit (optional): Maximum results (1-10, default: 5) - Returns: Formatted list of questions with scores |
| 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 string - language (optional): Filter by programming language - limit (optional): Maximum results per category (1-10, d |
| search_npm | Search npm registry for JavaScript packages. - Parameters: - query (required): Search query string - limit (optional): Maximum results (1-10, default: 5) - Returns: Package information including version, description, and |
| 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 string - limit (optional): Maximum results per platform (1-5, default: 3) - Returns: Combined results from all |
| Debugging | Since MCP servers communicate over stdio, debugging can be challenging. Use the MCP Inspector for detailed request/response monitoring: |
| 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 |
{
"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": []
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| GITHUB_TOKEN | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.