Brave Search MCP Server
Brave's official MCP server that gives AI agents the Brave Search API
Searches the whole web, news, images, videos and local businesses, not only library documentation.
Context7 is an MCP server from Upstash. It gives AI coding assistants up-to-date, version-specific documentation and code examples for the libraries you use. Add "use context7" to a prompt, or name a library ID such as /vercel/next.js. The server has two tools: resolve-library-id and query-docs.
It works in two modes: as an MCP server, or as the ctx7 CLI with a skill for your agent (set up with npx ctx7 setup). Use the hosted server at mcp.context7.com, or run it on your computer with Node.js. The docs give setup steps for more than 30 clients, including Cursor, Claude Code, VS Code and Codex.
The MCP server code is open source under the MIT licence. The API backend, parser and crawler are private. Plans (USD): Free, $0, 1,000 API calls a month, public repositories. Pro, $10 per seat per month, 2,000 calls per seat, then $5 per 1,000 calls, private repositories at $5 per 1M parsing tokens. Enterprise, custom price, with SSO and self-hosting.
Developers who use AI coding assistants such as Cursor, Claude Code or VS Code and want current library docs in their prompts. The Pro plan is for teams with private repositories; Enterprise is for companies that need SSO or self-hosting.
Returns version-specific library docs and code examples by library ID; Firecrawl MCP scrapes general web pages. Context7's free plan has 1,000 API calls a month.
Gives curated, version-specific library documentation instead of web search results, and has a free plan with no per-request charge.
The MCP server code is open source (MIT) and can run on your own computer; Figma's server code is not published and its calls are rate-limited by Figma plan and seat.
Brave's official MCP server that gives AI agents the Brave Search API
Searches the whole web, news, images, videos and local businesses, not only library documentation.
Official Firecrawl MCP server: AI agents search, scrape and crawl the web
Reads any web page or site, not only library documentation, and can monitor pages for changes on a schedule.
토론
토론에 참여하려면 로그인하세요.