Mumo MCP server

What it does

mumo is an MCP server that runs multi-model deliberations across seven AI models (Claude, GPT, Gemini, Grok, Qwen, GLM, Kimi) in parallel. It is designed for developers and teams who need to consult multiple language models on contested decisions such as architecture choices, plan reviews, and strategic questions.

• Run architecture reviews by submitting a design problem and receiving parallel perspectives from seven different models.
• Resolve planning disagreements by creating a deliberation session and waiting for multiple models to weigh in on competing approaches.
• Validate strategic decisions by appending context rounds to a session and collecting model consensus on high-stakes choices.

Tools this server exposes

Tool	Does
create_deliberation	Start a new multi-model deliberation session with an initial prompt.
wait_for_round	Poll for completion of a deliberation round across all models.
append_round	Add follow-up context or questions to an ongoing deliberation session.
get_session	Retrieve the full contents and history of a specific deliberation session.
list_sessions	List all deliberation sessions associated with the current user.
list_models	Display the available AI models that participate in deliberations.
get_credit	Check the current API credit balance for the user.

Before you enable it

An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.