What is MCP? The Model Context Protocol is an open standard that lets AI models securely connect to external tools, APIs, databases, and filesystems. Think of it as a USB-C port for AI — a universal interface that any model can use to interact with the world.
This repo currently indexes 7,493 unique MCP server links from the category docs. The README stays lightweight while the full directory lives in docs/*.md, data/catalog.json, and the registry MCP server.
This repo is both a community directory and an agent-ready index. Humans add MCP servers in markdown category pages; the indexer turns those entries into structured data that agents can search, inspect, and use to draft install configs.
How it works:
- The source of truth is the category markdown under
docs/*.md. - Each server entry is parsed from a markdown bullet with a link and description.
npm run catalog:buildgeneratesdata/catalog.jsonwith normalized server metadata.npm run profiles:buildgeneratesdata/profiles/*.jsonfor stable per-server profiles.npm run registry:mcpstarts a local registry MCP server withsearch_servers,get_server_profile, andget_install_configtools.
That means contributors still submit a normal awesome-list entry, but better metadata makes the entry more useful to agents. When possible, include install command, transport, auth type, supported clients, tool count, license, docs URL, and public remote endpoint. See the MCP Index Metadata Contribution Guide for examples.
We welcome MCP server submissions. To add your server:
- Pick the best category from Browse by Category.
- Open that category page under
docs/. - Add one markdown bullet using this format:
- [Server Name](https://github.com/owner/repo): Brief description of what the MCP server lets an agent do. Install: `npx your-package`. - Search the repo for your URL or project name to avoid duplicates.
- Open a pull request.
Good entries answer these questions in one or two sentences:
- What can an agent do with this server?
- How does a user install or connect to it?
- Does it use
stdio,sse, orstreamable-http? - Does it require an API key, OAuth, or no auth?
- Which MCP clients does it support?
Generated files such as data/catalog.json and data/profiles/*.json are maintained by the indexer. If you only add a server entry, editing the relevant docs/*.md category page is enough for the PR.
For maintainers validating a metadata/indexer change:
npm run catalog:build
npm run profiles:build
npm test
npm run typecheck
The README is now a lightweight entry point. Browse the full directory in the category pages below, or use data/catalog.json and the registry MCP server for agent-native search.
| Category | Listed entries | Full list |
|---|---|---|
| AI & LLM Integration | 1,619 | Browse |
| Art, Culture & Media | 78 | Browse |
| Browser Automation & Web Scraping | 275 | Browse |
| Build & Deployment Tools | 88 | Browse |
| Cloud Platforms & Services | 371 | Browse |
| Code Analysis & Quality | 105 | Browse |
| Code Execution | 165 | Browse |
| Communication & Messaging | 327 | Browse |
| Content Management Systems | 59 | Browse |
| Data Analysis & Business Intelligence | 238 | Browse |
| Databases | 290 | Browse |
| Developer Productivity & Utilities | 393 | Browse |
| Filesystems | 56 | Browse |
| Finance & Crypto | 408 | Browse |
| Frameworks | 244 | Browse |
| Gaming | 106 | Browse |
| Hardware & IoT | 59 | Browse |
| Healthcare & Life Sciences | 57 | Browse |
| Infrastructure | 156 | Browse |
| Knowledge Management & Memory | 559 | Browse |
| Location & Maps | 89 | Browse |
| Marketing, Sales & CRM | 167 | Browse |
| Monitoring & Observability | 83 | Browse |
| Multimedia Processing | 204 | Browse |
| Operating System & Command Line | 106 | Browse |
| Project & Task Management | 219 | Browse |
| Science & Research | 106 | Browse |
| Search | 168 | Browse |
| Security | 121 | Browse |
| Social Media & Content Platforms | 107 | Browse |
| Sports | 6 | Browse |
| Travel & Transportation | 45 | Browse |
| Utilities & Helpers | 353 | Browse |
| Version Control | 76 | Browse |