GitHub MCP Server
Lets your AI agent read code, manage issues and pull requests, and check builds on GitHub
by GitHub
MCP servers: connect the tools you need
Choose a connector when the missing part of your task is access to another tool or data source. Check both sides of the connection: the server and the application that will use it.
Start with the operation
Reading repository files, opening a browser and updating a notes page need different capabilities. Look for the exact operation in the server's documentation; a service name alone does not tell you which actions it exposes.
Check local and remote setup
A local server needs an executable and its dependencies in the environment where the client starts it. A remote server needs the documented endpoint and authentication method. Client support for transports and features varies.
Inspect the account access
Find out whether the connection can read or write and which account it uses. Then inspect the client's server status and available tools. A successful connection does not establish that every requested operation is available.
Examples from the Library
These pages explain the projects and link to their creators. The selection illustrates different uses; it is not a ranking.
Notion MCP
Lets your AI agent search, read and edit pages in your Notion workspace
by Notion
Playwright MCP
Lets your AI agent open web pages, click, type and fill in forms in a real browser
by Microsoft
Context7
Gives your coding agent current, version-specific docs and code examples for libraries
by Upstash
Browse all connectors to filter by task, cost and setup effort.
Before you install
An MCP server is missing or disconnected explains the next checks. If you need help with a specific setup, describe the task and where it stopped.
Source
Model Context Protocol introduction. Project-specific sources and installation steps are on each Library page.