#60 · Primary category: AI Gateway & API Infrastructure
mcphub
A unified hub for centrally managing and dynamically orchestrating multiple MCP servers/APIs into separate endpoints with flexible routing strategies.
Project last updated:08/28/26
GitHub Stars
2.3K
Forks
290
Contributors
41
License
Apache-2.0
Why we included this project
Anyone running more than a few Model Context Protocol servers ends up duplicating client wiring and chasing credential drift. MCPHub puts those servers behind one management plane and re-exposes them as HTTP/SSE routes, so a client can reach everything, a logical group, or a single server through a predictable URL. The web dashboard gives you per-server control over which tools, prompts, and resources each group can see, and config changes apply without restarting servers. It also covers the operational side: bearer-token auth, OAuth in both client and server modes, compression for large tool outputs, and a PostgreSQL-backed database mode for production deployments. If you prefer the command line, the bundled CLI can manage the hub and call it from CI scripts.
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.