What are the runtime requirements?
Node.js >= 20.11.0 and npm >= 10.0.0 are required. A GitHub personal access token is optional but recommended to avoid rate limits.
@nahmanmate
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"code-research-mcp-server": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@nahmanmate/code-research-mcp-server",
"--client",
"claude"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
A Model Context Protocol server that provides tools for searching and accessing programming resources across multiple platforms. It integrates with Stack Overflow, MDN Web Docs, GitHub, npm, and PyPI to help LLMs find relevant code examples, documentation, and packages.
Install using Smithery (npx -y @smithery/cli install @nahmanmate/code-research-mcp-server --client claude) or manually by cloning the repository and running npm install && npm run build. Then configure the server in your MCP settings file (e.g., Claude Desktop or VSCode) with the node command pointing to the built index.js. Optionally set a GITHUB_TOKEN environment variable. Once configured, invoke any of the six search tools (e.g., search_stackoverflow, search_github, search_all) via the MCP client.
search_all tool.Node.js >= 20.11.0 and npm >= 10.0.0 are required. A GitHub personal access token is optional but recommended to avoid rate limits.
Results are cached using `node-cache` with a default TTL of one hour. Cache keys are specific to each query/limit combination, and caching strategies are platform-specific.
The server integrates with Stack Overflow, MDN Web Docs, GitHub, npm, and PyPI. Tools are available for each platform individually, plus a combined search tool.
No, it is optional. A GitHub personal access token used via the `GITHUB_TOKEN` environment variable prevents rate limiting when searching GitHub.
Yes, use `npm run watch` for auto-rebuild on changes, or `npm run inspector` to launch the MCP Inspector for debugging request/response monitoring.

Extract products, prices, images and reviews from any page in one click — or connect your AI agent and let it do the scraping for you. Works great for: - Ecommerce: extract every product from a Shopify, WooCommerce or

Privacy-first, cookieless web analytics hosted in the EU. Query visitors, pages, traffic sources, countries, goals, funnels and live traffic for your sites, and create sites, goals and funnels — 25 tools over OAuth.

Real, calibrated win-rate predictions, pick recommendations, counters, synergy and tier lists for Dota 2, Deadlock and Marvel Rivals, from production models trained on ~20M matches. Free hosted endpoint (Streamable HTTP)
Texas RRC oil & gas wellbores: API numbers, completion dates, depth, plug status
Hosted YouTube MCP server for search, video metadata, channel data and timestamped transcripts. Connect Claude, Cursor or other MCP clients with HasData; no YouTube API key required.
评论