MCP Platform

The OpenModels MCP Platform is a community-driven registry for Model Context Protocol (MCP) servers. It provides a centralized catalog where developers can discover, compare, and integrate MCP servers into their AI workflows.

What is MCP?

The Model Context Protocol is an open standard that enables AI assistants to interact with external tools, data sources, and services through a unified interface. MCP servers expose:

Tools — functions that AI agents can invoke (e.g., run tests, query databases, search the web)
Resources — data sources for AI agent consumption (e.g., file access, API responses)
Prompts — reusable prompt templates with configurable arguments

Why OpenModels MCP?

Discover — browse and search a curated catalog of MCP servers by category, transport type, or keyword
Compare — evaluate servers side by side across capabilities, tools, and compatibility
Connect — generate IDE configuration snippets for one-click integration
Contribute — submit new servers via pull request with automated validation

Platform Features

Feature	Description
Catalog	Searchable registry at openmodels.run/mcp
Detail pages	Full server info with tools, resources, and prompts
IDE configs	Auto-generated connection snippets for 6 IDEs
Comparison	Side-by-side comparison of 2–4 servers
API access	RESTful API at `/api/v1/mcp/*`
CI validation	Automated schema validation on every PR

Supported Transports

MCP servers communicate via one of three transport protocols:

Transport	Description
`stdio`	Standard input/output — local process communication
`sse`	Server-Sent Events — HTTP-based streaming
`http-streaming`	HTTP streaming — bidirectional HTTP communication

Next Steps

Getting Started — browse, search, and connect MCP servers
Contributing — submit a new server to the registry
Schema Reference — full server definition format
IDE Integration — setup guides for each supported IDE