Claude MCP Servers Directory - Model Context Protocol

What is MCP?

The Model Context Protocol (MCP) is an open standard that enables AI assistants to securely connect with external data sources and tools. Think of it as USB-C for AI - a universal way to provide context.

Reference Servers (Official)

Everything

Reference/test server with prompts, resources, and tools

Official

Fetch

Web content fetching and conversion for efficient LLM usage

Official

Filesystem

Secure file operations with configurable access controls

Official

Git

Tools to read, search, and manipulate Git repositories

Official

Memory

Knowledge graph-based persistent memory system

Official

Sequential Thinking

Dynamic and reflective problem-solving through thought sequences

Official

Time

Time and timezone conversion capabilities

Official

Popular Community Servers (25+)

GitHub

Interact with GitHub repositories, issues, and pull requests

Community

Slack

Read and send messages, manage channels in Slack workspaces

Community

PostgreSQL

Query and manage PostgreSQL databases

Community

Puppeteer

Browser automation for web scraping and testing

Community

Brave Search

Web search capabilities using Brave Search API

Community

Google Drive

Access and manage files in Google Drive

Community

Google Maps

Location services and mapping capabilities

Community

AWS

Integration with Amazon Web Services

Community

Azure

Microsoft Azure cloud services integration

Community

SQLite

Query and manage SQLite databases

Community

Sentry

Error tracking and monitoring integration

Community

GitLab

Interact with GitLab repositories and CI/CD

Community

Redis

In-memory data structure store operations

Community

EverArt

AI image generation capabilities

Community

Atlassian

Interact with Jira and Confluence

Community

Notion

Manage Notion pages and databases

Community

Discord

Interact with Discord servers and channels

Community

Docker

Manage Docker containers and images

Community

Apollo

Connect GraphQL APIs to AI agents

Community

Auth0

Identity and access management integration

Community

Playwright

Browser automation using accessibility tree (Microsoft)

Community

Context7

Up-to-date code documentation for LLMs

Community

Supabase

Connect to Supabase projects and manage databases

Community

Figma

Generate code from Figma designs and components

Community

Serena

Coding agent toolkit with semantic code analysis

Community

Frequently Asked Questions

What is Claude MCP?

Claude MCP (Model Context Protocol) is an open standard that enables AI assistants like Claude to securely connect with external data sources and tools. It provides a universal way for AI assistants to access context from various services and applications.

How do I install an MCP server?

To install an MCP server, you'll need to add its configuration to your Claude Desktop config file. Each server page provides detailed installation instructions including the required npm packages and configuration settings. Simply copy the provided configuration into your Claude Desktop settings.

What's the difference between Official and Community servers?

Official servers are maintained by Anthropic and the MCP core team, ensuring high quality and regular updates. Community servers are created and maintained by third-party developers and offer additional integrations and features beyond the official servers.

Are MCP servers secure?

MCP servers run locally on your machine and you control what data they can access. Official servers are thoroughly vetted by Anthropic. For community servers, review the source code and permissions before installation. Always use API keys and credentials securely.

Can I use multiple MCP servers at the same time?

Yes! You can install and use multiple MCP servers simultaneously. Simply add each server's configuration to your Claude Desktop config file, and Claude will have access to all of them during your conversations.

Do I need coding knowledge to use MCP servers?

Basic familiarity with configuration files and command-line operations is helpful, but not strictly required. Each server page provides copy-paste configurations and step-by-step instructions. For most servers, you'll need to install Node.js and edit a JSON configuration file.

Which MCP servers should I start with?

Popular starting points include the Filesystem server for local file access, the Fetch server for web content, and the GitHub server if you work with code repositories. Choose servers based on your specific workflow and needs.

Can I create my own MCP server?

Yes! MCP is an open standard and you can create custom servers to integrate any data source or tool. Check the official MCP documentation and server examples on GitHub to get started with building your own server.