Skip to content

MCP Server Directory

Browse and search Model Context Protocol (MCP) servers by category, with GitHub stars, transport type and copyable install commands.

MCP Server Directory

39 servers|6 categories
MCP specification
39 servers
Sort:
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+2
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+2
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
+1
stdio
stdio

Category breakdown

Official MCP servers repo
Official12
Developer Tools6
AI & LLM4
Data & APIs6
Productivity5
Community6
GitHub stars as of 2026-10-03Descriptions and install commands are curated. Check each server's repository before installing.

What this tool does

Production-ready MCP servers are easiest to identify by maintainer and maintenance status. This directory tracks 39 Model Context Protocol servers across 6 categories with install commands and GitHub activity. Official reference servers from the Model Context Protocol project and vendor-owned servers such as Cloudflare, Stripe, and Supabase are the safest starting points; 8 early reference servers are now archived upstream and should not be used for new deployments.

Updated . Provided as is. Check the output before you rely on it in production.

How to use MCP Server Directory

  1. 1

    Browse by category

    Filter servers by category: Official, Developer Tools, AI & LLM, Data & APIs, Productivity or Community.

  2. 2

    Copy the install command

    Expand a server to see its install command and copy it. Pin a version before you rely on a server in production.

  3. 3

    Check the repository

    Every entry links to its GitHub repository. Read the README there for required environment variables, API keys and runtime versions.

  4. 4

    Search and sort

    Search by name, description, author or tag, and sort the list to find what you need.

Questions and answers

What is MCP Server Directory?
MCP servers are small programs that give AI assistants such as Claude access to tools and data. This directory lists them by category with author, GitHub stars, transport type and a copyable install command, and can be searched by name, description, author or tag and sorted by stars, name or date added.
What is the Model Context Protocol (MCP)?
MCP is an open protocol that lets AI assistants connect to external tools and data through servers that expose capabilities such as file access, database queries or API calls. This directory lists MCP servers with install commands and links to their source repositories.
For AI agents: how to call this tool

Machine-readable contract, endpoints and examples. Humans can ignore this section.

Best Path For Builders

Browser workflow

Runs instantly in the browser with private local processing and copy/export-ready output.

Browser Workflow

This tool is optimized for instant in-browser execution with local data handling. Run it here and copy/export the output directly.

/mcp-directory/

For automation planning, fetch the canonical contract at /api/tool/mcp-directory.json.

Which MCP servers are production ready?

There is no official certification for MCP servers, so "production ready" comes down to verifiable signals: who maintains the server, whether it is actively maintained or archived, how widely it is deployed, and whether its permission scope fits your threat model. The table below lists the 31 actively maintained servers in this directory, sorted by GitHub stars. Star counts refresh weekly; data as of 2026-09-27.

Actively maintained MCP servers (31)

Server Maintainer Category Transport GitHub Stars
Filesystem Model Context Protocol Official stdio 91.0k
Memory Model Context Protocol Official stdio 91.0k
Fetch Model Context Protocol Official stdio 91.0k
Sequential Thinking Model Context Protocol Official stdio 91.0k
Git Model Context Protocol Developer Tools stdio 91.0k
Everything Model Context Protocol Community stdio 91.0k
Context7 Upstash AI & LLM stdio 62.6k
Chrome DevTools ChromeDevTools Developer Tools stdio 52.9k
Playwright Microsoft Data & APIs stdio 37.8k
GitHub GitHub Official stdio 33.3k
Serena Oraios AI Community stdio 30.0k
FastMCP Prefect AI & LLM stdio 28.0k
n8n Workflows Romuald Członkowski Data & APIs stdio 23.0k
Figma Context Graham Lipsman AI & LLM stdio 15.9k
Firecrawl Firecrawl Data & APIs stdio 7.5k
Exa Search Exa Labs Community stdio 5.1k
Notion Notion Productivity stdio 4.7k
Obsidian Markus Pfundstein Productivity stdio 4.5k
Cloudflare Cloudflare Data & APIs stdio 4.3k
Supabase Supabase Data & APIs stdio 2.9k
MySQL Ben Borla Community stdio 2.1k
Stripe Stripe Data & APIs stdio 1.9k
Kubernetes Suyog Sonwalkar Developer Tools stdio 1.6k
Google Calendar Nathan Spady Productivity stdio 1.2k
Sentry Sentry Developer Tools stdio 906
Docker Christian Kreiling Developer Tools stdio 746
Todoist Abhiram Nair Productivity stdio 393
Linear Jeremy Hadfield Developer Tools stdio 347
AWS MCP Servers AWS Samples Community stdio 244
LangChain Tools Andrew Wason AI & LLM stdio 205
Raygun Raygun Community stdio 22

Reference servers maintained by the Model Context Protocol project share the star count of the modelcontextprotocol/servers monorepo. Source: each server's GitHub repository, refreshed 2026-09-27.

How do I evaluate an MCP server before production use?

  1. Check the maintainer. Servers owned by the vendor of the underlying service (GitHub, Cloudflare, Stripe, Supabase, Microsoft's Playwright) track API changes fastest.
  2. Check maintenance status. Several early reference servers are archived and no longer receive fixes — archived servers are listed below and should be treated as end-of-life.
  3. Review the permission scope. A filesystem or database server should be configured with the narrowest possible access (allowed directories, read-only credentials) before an agent can call it.
  4. Prefer stdio transport for local, single-user setups and audit any server that makes outbound network calls with your data.
  5. Pin versions. Install commands like npx -y fetch the latest release; pin an exact version in production so server behavior does not change under your agent.

Which MCP servers are archived?

These 8 servers are archived upstream. They may still work today, but they no longer receive security fixes or API updates, so do not build new production deployments on them:

PostgreSQL, SQLite, Brave Search, Google Maps, Slack, Puppeteer, EverArt, Google Drive.