🚀 MCPOmni Connect - Universal Gateway to MCP Servers

What is MCPOmni Connect?

MCPOmni Connect is a universal command-line interface (CLI) and Python library that integrates multiple MCP servers, AI models, and transport protocols into a single interface. It runs on Python 3.10+ and is designed for developers building MCP-powered applications.

How to use MCPOmni Connect?

Install via uv add mcpomni-connect or pip install mcpomni-connect, set the LLM_API_KEY environment variable, and configure servers in servers_config.json. Start the CLI with mcpomni_connect or run the FastAPI server example with uv run examples/fast_api_iml.py. Use the web client at examples/index.html after starting the server.

Key features of MCPOmni Connect

• Multi-protocol support: stdio, SSE, streamable HTTP, Docker, NPX
• Authentication: OAuth 2.0, Bearer token, custom headers
• ReAct and Orchestrator agent modes for autonomous task execution
• Integration with OpenAI, OpenRouter, Groq, Gemini, DeepSeek models
• Redis-powered persistent memory and chat history file storage
• Dynamic tool discovery, cross-server routing, and prompt management

Use cases of MCPOmni Connect

• Build a custom backend with FastAPI that connects to multiple MCP servers
• Run an autonomous ReAct agent to execute complex tasks without human intervention
• Orchestrate multi-step workflows across several MCP servers using the Orchestrator mode
• Use the CLI to interact with MCP resources, tools, and prompts interactively
• Deploy a web chat interface backed by MCP servers with streaming responses

FAQ from MCPOmni Connect

What is MCPOmni Connect and how is it different from other MCP clients?

It is a unified CLI and library that connects to multiple MCP servers, supports various transport protocols, and includes built-in AI agent modes (ReAct and Orchestrator) for autonomous tool use and task planning.

Which AI models are supported?

It supports models from OpenAI, OpenRouter, Groq, Gemini, and DeepSeek. The custom ReAct agent also handles models without native function calling.

How do I install and configure MCPOmni Connect?

Install via uv add mcpomni-connect or pip install mcpomni-connect. Set the LLM_API_KEY environment variable and optionally configure Redis for persistent memory. Create a servers_config.json file to define MCP server connections.

Is MCPOmni Connect free and open source?

Yes, it is released under the MIT license and is available on PyPI. There is no pricing; you only need an API key for the LLM provider you choose.

What authentication methods does it support for MCP servers?

It supports