Mumo MCP

What the Mumo MCP MCP server does

Mumo MCP MCP server connects an MCP client to a multi-model deliberation service. An agent can submit a question, receive responses from models across different labs, and inspect typed reactions showing where participants agree, challenge an argument, want to explore an idea, or identify a core point. Supported model providers mentioned by the project include Claude, GPT, Gemini, Grok, DeepSeek, and Kimi, with the exact available models dependent on the account.

The service is intended for decisions that benefit from independent review rather than a single model response. Examples include comparing architecture options, reviewing a technical plan or specification, testing a strategy, and finding weaknesses before launch. The panel is advisory; the project recommends reading the disagreement and claim map instead of treating the majority view as automatically correct.

How it works

A typical interaction begins with create_deliberation. That call returns a session ID and round ID immediately while the participating models work in the background. The client then calls wait_for_round, which polls until the round finishes and returns the model responses together with the claim map. The project notes that panels commonly take 15 to 120 seconds, so a delayed result is expected.

Follow-up analysis uses append_round. The next round can include typed snippets labeled KEEP, EXPLORE, CHALLENGE, CORE, or SHIFT to direct attention. Session state, including rounds, responses, snippets, and claim maps, is available through get_session. Completed sessions can be published with share_session, which returns a public page and Markdown representations. list_sessions retrieves prior sessions, while list_models and get_credit expose available models, pricing, and remaining credit.

Setup and configuration

Mumo MCP MCP server is hosted at https://mumo.chat/api/mcp; there is no local process to run. Configure an MCP client that supports Streamable HTTP and custom headers with that URL and an Authorization header using a bearer token. API keys are created at the Mumo settings API-key page after signing in, and the documented keys begin with mmo_live_.

The server allows initialize and tools/list without authentication, so a client can inspect its interface before a key is created. Tool calls require the authorization header. The repository provides installation pages for Claude Code, Cursor, Codex, and VS Code, as well as several additional hosts. Other MCP clients can use the generic Streamable HTTP configuration when they support custom headers.

Tools and capabilities

• Start asynchronous multi-model deliberations with create_deliberation.
• Wait for completed rounds and retrieve responses plus claim maps.
• Add directed follow-up rounds using typed steering snippets.
• Read complete session state and list earlier sessions.
• Publish sessions with web and machine-readable Markdown outputs.
• Inspect account models, model pricing, and credit balance.

Limitations and notes

Mumo MCP MCP server requires an API key for tool calls and uses account credit for access; the README mentions free monthly credit but does not specify an amount. Model availability and pricing are account-dependent. Results are not immediate, and the panel should be treated as advisory rather than as an automated decision-maker.

The repository also contains the source for host-specific skills and build scripts that teach supported agents when and how to convene a panel. Those files are separate from the hosted MCP endpoint. Changes to rendered client skills are generated from the shared template rather than edited directly in each client repository.