mumo
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mumoConvene a panel to review our event-driven architecture proposal."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mumo — multi-model deliberation over MCP
Your agent sends a question to models from different labs — Claude, GPT, Gemini, Grok, DeepSeek, Kimi, and more — and gets back their full responses plus typed cross-model reactions. The participating models react to each other directly and explain, in their own words, what they agree with, challenge, or want to explore further. Built for architecture, plan/spec review, strategy, and pre-launch pressure tests. Free monthly credit; API key required.
The server is remote. There is nothing to run locally.
https://mumo.chat/api/mcpInstall
One-click, per host — each page walks through the key and the client's own install flow:
Host | Install page |
Claude Code | |
Cursor | |
Codex | |
VS Code (Copilot) | |
Grok Bot | |
Hermes Agent | |
OpenClaw | |
Anything else |
Any MCP client that supports Streamable HTTP with a custom header:
{
"mcpServers": {
"mumo": {
"url": "https://mumo.chat/api/mcp",
"headers": {
"Authorization": "Bearer mmo_live_YOUR_KEY_HERE"
}
}
}
}Get a key at mumo.chat/settings/api-keys (sign-in required; keys start with mmo_live_). initialize and tools/list work without a key, so your client can inspect the tools before you create one; tool calls need the header.
Related MCP server: model-council-mcp
Tools
Tool | What it does |
| Start a deliberation. Returns an ack immediately ( |
| Block on cheap progress polling until the round is done, then return every model's response and the claim map. |
| Add a follow-up round, optionally steered with typed snippets (KEEP / EXPLORE / CHALLENGE / CORE / SHIFT). |
| Read full session state: rounds, responses, snippets, claim maps. |
| Share a session at its public URL; returns the page plus |
| List your prior sessions. |
| List the models available to your account, with pricing. |
| Read your credit balance. |
Full reference, request and response shapes, and per-client notes: https://mumo.chat/docs/mcp. Machine-readable descriptors: /.well-known/mcp.json (manifest) and /api/mcp/server-card (MCP Server Card). Registry name: chat.mumo/mcp.
The loop
create_deliberationwith the question, written in the operator's first person ("I'm deciding whether to…").wait_for_round— panels take 15–120 s; a long wait is normal.Read the claim map before the prose. Steer with
append_roundand snippets, or stop.
The panel is advisory. Read the disagreement; don't defer to whichever side has more votes.
This repo: the client baseline
Beyond the server, mumo ships a skill for each host that teaches the agent when to convene a panel and how to read one. This repo is the source of truth for that skill: one tokenized SKILL.template.md plus a per-client overlay, rendered into each sibling client repo by the build script in scripts/. Never edit a client's SKILL.md directly — edit here and re-render.
Client repo | Renders to |
| Claude Code plugin |
| Cursor plugin |
| Codex plugin |
| VS Code extension |
| Hermes Agent skill |
| OpenClaw skill |
Contents
skills/mumo/
├── SKILL.template.md # tokenized baseline (the source of truth)
├── playbooks/ # shared cognitive-shape playbooks
└── references/ # shared reference docs (claim maps, snippets, takeaway, etc.)
scripts/
├── build-skill.js # renderer: template + per-client overlay -> client SKILL.md
├── README.md # how the build system works
└── clients/ # per-client configs + Setup/Frontmatter partials
server.json # Official MCP Registry descriptor (chat.mumo/mcp)The template uses {{TOKEN}} markers for per-client substitution points (application name, moderator example, install URL, tool-naming registry note, etc.). Each scripts/clients/<client>.json fills them in.
Building
node scripts/build-skill.js # render to all six sibling client repos
node scripts/build-skill.js --target <client> # render one
node scripts/build-skill.js --verify-all # check for drift across all six (use in CI)See scripts/README.md for details (token reference, adding a new client, etc.).
Editing
Shared kernel changes → edit
skills/mumo/SKILL.template.md. Re-render to propagate.Per-client overlay changes (
## Setupbody, frontmatter, application name, moderator example, install URL, tool-naming note) → editscripts/clients/<client>/partials orscripts/clients/<client>.jsontokens. Re-render.Shared playbooks / references → edit
skills/mumo/playbooks/orskills/mumo/references/. Currently propagated manually; build-system handling is a follow-up.
Architecture
The shared-sections + per-client-overlay model is documented in docs/MCP_CLIENTS.md in the main mumo repo. The 2026-05-20 audit at docs/audits/2026-05-20-mcp-skill-delta.md enumerates exactly which sections are shared vs. per-client.
Links
Product — https://mumo.chat
For agents — https://mumo.chat/for-agents
MCP reference — https://mumo.chat/docs/mcp
REST API — https://mumo.chat/docs/api · OpenAPI — https://mumo.chat/openapi.json
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.
Commission a multi-model AI spec committee from your agent; get rubric-scored, build-ready specs.
Convene a panel of expert AI personas to debate any decision from every side.
Multi-expert decision intelligence with transparent synthesis and auditable workflows.
Related MCP Servers
- AlicenseAqualityAmaintenanceEnables Claude to chat with various AI models and obtain multi-model consensus for complex decisions.4735 npm2MIT
- AlicenseAqualityAmaintenanceRoutes questions to multiple AI models (local and cloud) and synthesizes their answers in individual, categorized, or deconflicted modes.91Apache 2.0
- AlicenseNot gradedqualityAmaintenanceEnables querying multiple AI models simultaneously and returns all answers unmerged for the user to weigh.4MIT
- AlicenseAqualityAmaintenanceRoutes questions to a council of AI models (local and cloud) and synthesizes their answers in five configurable modes: individual, categorized, deconflicted, pooled, and dialectic.9Apache 2.0