AI Agents

MCP serversGive your agent tools it can trust

An MCP server connects your AI agent to something outside the chat: your GitHub issues, a real browser, your database, the current docs for a library.

Each one here comes with the config for the tool you use, what it can read and change, and how to make it read-only when it has that option.

Works with

5 MCP servers in 3 categories

Code

1 MCP server

Repositories, pull requests, issues and files: reading and changing the code your agent works on.

Filesystem MCP Server

The reference Filesystem MCP server gives your AI agent file access limited to the folders you name. Ideal for Claude Desktop and for learning MCP.

See server

Browser

2 MCP servers

A real browser your agent can drive: click through your app, read the console and network, profile a page.

Playwright MCP Server

Microsoft's Playwright MCP server lets your AI agent drive a real browser: open pages, click, fill in forms and read each page as an accessibility tree.

See server

Chrome DevTools MCP Server

Google's Chrome DevTools MCP server lets your AI agent debug a live Chrome: console, network requests, performance traces and Lighthouse audits.

See server

Docs

2 MCP servers

Current documentation for the libraries and platforms you use, so your agent stops guessing at APIs.

Context7 MCP Server

Context7's MCP server gives your AI agent current, version-specific library docs and code examples, so it stops inventing APIs that do not exist.

See server

Cloudflare Docs MCP Server

Cloudflare's documentation MCP server lets your AI agent search current Cloudflare docs for Workers, R2, D1 and the rest. No account or API key needed.

See server