The largest community-curated list of MCP servers, sorted by category from databases to browsers. The place to look for an existing server before writing your own.
All repositories
MCPfirecrawl
firecrawl-mcp-server
Firecrawl's official MCP server: scraping, search and site crawling for an agent. Offers a hosted keyless free tier or a local run through npx.
Who it is for
For people who need an agent to read websites and collect data from the web.
How to start
- Connect the hosted server at
https://mcp.firecrawl.dev/v2/mcpin your client settings. - Or run it locally:
env FIRECRAWL_API_KEY=fc-YOUR_API_KEY npx -y firecrawl-mcp. - For the remaining tools get a Firecrawl API key and pass it through the client settings.
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+170Sep 6 — Oct 6
Author's description
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
More in «MCP»
Reference MCP servers from the protocol team: memory, git, filesystem and more. A solid pattern for how a server is built and a ready set to start with.
Feeds fresh, version-specific library docs into the prompt so the model stops inventing outdated APIs. Works as an MCP server or through a CLI with a skill.
Hands Chrome DevTools to an agent: network, console, performance, screenshots. The agent does not just click, it sees why a page is slow or broken.
A Playwright-based MCP server that lets an agent drive a browser through page structure rather than screenshots. Good for testing sites and automating web actions.
GitHub's official MCP server: an agent reads repositories, issues and pull requests and works with them. Comes as a hosted version from GitHub and a local one in Docker.