# mumo

Coordinates multi-model debates across Claude, GPT, and Gemini with cross-model rebuttals. Useful for pressure-testing architecture plans before rollout.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: mumo-chat
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/mumo-chat/mumo-mcp
- Updated: 2026-09-09
- HTML: https://affpapa.org/en/nevibecode/mcp/mumo

## What it does

mumo operates as a hosted endpoint at `https://mumo.chat/api/mcp`, avoiding local processes or background binaries. An agent dispatches a problem statement to multiple labs including Claude, GPT, Gemini, Grok, DeepSeek, and Kimi. The participating models formulate answers and critique each other's claims directly.

Deliberations run asynchronously. The agent initiates a session via `create_deliberation`, then blocks with `wait_for_round` while the panel deliberates. Panels take 15 to 120 seconds. Outputs return as a structured claim map, which can be steered into another round using `append_round` alongside typed tags like KEEP, EXPLORE, or CHALLENGE.

Tool execution fails without an API key starting with `mmo_live_`, even though `initialize` and `tools/list` respond freely. The service includes a recurring monthly credit allowance for testing.

## Requirements
- Remote server: `https://mumo.chat/api/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mumo https://mumo.chat/api/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add mumo --url https://mumo.chat/api/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "mumo": {
            "url": "https://mumo.chat/api/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "mumo": {
            "type": "http",
            "url": "https://mumo.chat/api/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http mumo https://mumo.chat/api/mcp
```

## When to use it
- gather cross-model critiques on system architecture drafts
- compare assessments from GPT, Claude, and Gemini on one decision
- highlight disagreements among competing models before product launch
- guide iterative deliberation rounds using KEEP and CHALLENGE snippets

## Example prompts
- Start a new discussion using `create_deliberation` on whether to adopt event sourcing for our payment service.
- Wait for the deliberation round to finish with `wait_for_round` and summarize the claim map disagreements.
- Check available panel models and account pricing via `list_models`.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md