#21 · Primary category: AI Gateway & API Infrastructure
modelcontextprotocol
Specification and documentation for the Model Context Protocol
Project last updated:08/29/26
GitHub Stars
9.1K
Forks
1.8K
Contributors
386
License
Other
Why we included this project
Before wiring an AI application to external tools, files, and databases, it pays to read the protocol definition most of the ecosystem now implements. This repo is the canonical home of that standard: the spec, the versioned TypeScript and JSON schemas, and the official documentation covering the architecture, message patterns, authorization, and transports. It is not deployable software, so don't expect a runnable service; its value is as the reference you consult when building an MCP server or client, or when deciding which community SDK to trust. Teams standardizing on one interface for tool calls, or checking how a vendor's implementation deviates from the spec, will find this the authoritative baseline. Because the protocol ships in dated releases, following this repo keeps your integration decisions aligned with what assistants and coding tools actually ship.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
OmniRoute
Open-source AI gateway: one endpoint, 290+ providers (90+ free), 500+ models, auto-fallback, token compression, MCP/A2A, works with Claude Code, Codex, Cursor, Cline, Copilot.
CLIProxyAPI
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.6 Series, Grok 4.5, Claude model through API
kong
🦍 The API and AI Gateway
novu
The open-source communication infrastructure for agents and products
GPT_API_free
Free API for large models, supports GPT, DeepSeek, etc., 10k free points daily, paid plans at 10-20% of official price.