Awesome MCP Servers
The largest community catalog of MCP servers: thousands of entries across dozens of categories (databases, browser automation, cloud, communication and more), tagged by language and scope.
Overview
Awesome MCP Servers is the reference community-curated list for the whole MCP server ecosystem: thousands of servers organized into dozens of categories (Databases, Browser Automation, Cloud Platforms, Communication, Coding Agents, Command Line, Developer Tools, Data Platforms and many more), each tagged with its implementation language and scope (local, cloud, embedded).
How it works
- Each entry follows a legend that marks whether a server is an official implementation, which language it's written in (Python, TypeScript, Go, Rust and more) and its scope (cloud, local, embedded).
- The list splits local servers (this repo, install and run yourself)
from hosted/remote servers (a companion list,
awesome-remote-mcp-servers). - A synced, searchable web version lives at glama.ai/mcp/servers.
- Quality varies enormously across thousands of community submissions, from official vendor servers (AWS, Cloudflare, Docker) to small hobby projects, so always check the individual server's own license and activity before relying on it, rather than trusting inclusion in the list as a quality signal.
Examples
"Browse the Databases category to find an MCP server for read-only
PostgreSQL access with schema inspection."
Licensing note
The list itself (README, structure) is MIT, maintained by punkpeye and 2,900+ contributors. Each linked server is a separate repo under its own license; verify it independently before use rather than assuming MIT applies to every entry.
Installation
There's nothing to install here: this is a curated list, not a server. Use it to find the right MCP server, then follow that server's own install steps.
- Browse the README by category, or use the synced web version at glama.ai/mcp/servers, to find a server that matches what you need.
- Open that server's own repository and follow its README for the install command and MCP client configuration.
- Check the server's own license and last commit date before relying on it, since quality varies a lot across thousands of community entries.
Related assets
Langflow
Visual Python platform for building and deploying AI agents and workflows, with full component source access, multi-agent orchestration and one-click export as an API or MCP server.
Graphify
Turns a codebase, plus its docs, PDFs, images, and video, into a queryable knowledge graph that a coding agent can traverse instead of grepping raw files, and never guesses silently: every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS so you know what was found versus inferred.
Context7
Pulls updated, version-specific documentation and code examples straight from the source into your prompt, so agents stop citing outdated APIs or hallucinating ones that don't exist.