AI & Machine Learning

mumo.chat

Facilitates structured multi-model AI deliberation sessions, enabling round-based comparisons and tracking of AI responses and claims.

1 endpoint8 known toolsFirst detected September 9, 2026Last detected September 9, 2026

ENDPOINT 1

https://mumo.chat/api/mcp

No auth detected

MCP server metadata

Name: mumo
Version: 1.1.0

Capabilities

tools.listChanged

Server instructions

mumo runs a deliberation across 2-3 frontier models from different labs and returns each model's full response plus a claim map of where they agree and diverge. Reach for it when the cost of being wrong exceeds the cost of deliberating: contested architecture and product decisions, plan and spec review, pre-launch red-teaming. Skip it for factual lookups, syntax, and routine edits. The loop: 1. `create_deliberation` returns an ack immediately, NOT results. Keep the `session_id` and `round_id` it returns and pass those exact values on. 2. `wait_for_round` blocks on cheap polling. Panels take 15-120s — a long wait is normal, not a hang, so tell the user to expect it. Branch on `structuredContent.recommended_client_action` rather than parsing prose. 3. `append_round` steers the next round. Attach `snippets` — verbatim quotes tagged KEEP, EXPLORE, CHALLENGE, CORE, or SHIFT — to point the panel at specific passages. This is the highest-signal thing a moderator does. Write the prompt in the operator's first person ("I'm deciding whether to…"), not case-study framing ("You are a CTO who…") — the second makes models grade a hypothetical and changes the answers. The panel is advisory. Read the disagreement; don't defer to whichever side has more votes.

Known tools 8

create_deliberation

Start a multi-model AI deliberation on a question or decision.

Inferred read-only

append_round

Add a follow-up round to an existing deliberation session.

Inferred read-only

wait_for_round

Wait for a deliberation round to finish, then return the full session.

Inferred read-only

get_session

Fetch the full state of a deliberation session including all rounds, responses, snippets, and claim maps.

Inferred read-only

list_sessions

List the caller's deliberation sessions, optionally filtered by status.

Inferred read-only

list_models

List the full model catalog.

Inferred read-only

share_session

Share a deliberation session at a public URL — anyone with the link can view it in the read-only reader deck.

Inferred read-only

get_credit

Fetch the caller's current credit wallet balance.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.mumo]
url = "https://mumo.chat/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "mumo": {
      "type": "http",
      "url": "https://mumo.chat/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: mumo
Remote MCP URL: https://mumo.chat/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "mumo": {
      "url": "https://mumo.chat/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "mumo": {
      "type": "http",
      "url": "https://mumo.chat/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "mumo",
  "transport": "streamable-http",
  "url": "https://mumo.chat/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.