It makes one model callable from inside another's conversation, with its own session and its own system prompt - so a Gemini or GPT read on the same problem is a tool call rather than a second window.
A Ruby gem that starts an MCP server in front of an LLM provider. You pick the provider, the model and optionally a base URL on the command line; the conversation it holds survives a restart as a named session, and it can itself connect out to other MCP servers so the model behind it can use their tools.
- A model from OpenAI, Google Gemini or any OpenAI-compatible endpoint exposed to your client as a tool
- Sessions that survive a restart, resumable by id and stored in a path you choose
- A session reset when the conversation should start clean
- System prompt text appended at launch, for pinning the persona the second model answers in
- Outbound MCP connections, so the model behind this server can call the tools of other servers you configure
- JSON-formatted logs written to a path you name
Ruby, with the gem installed from a Gemfile or with gem install. An API key for whichever provider you use - OpenAI, or Gemini under either of the two names Google uses - exported in the environment. Provider, model and base URL are flags on llm-mcp mcp-serve, so a Groq or other compatible endpoint is one launch option away.
One command plus a key — gem install llm-mcp, then supply credentials