{"id":"chat.mumo/mcp","slug":"chat-mumo-mcp","title":"mumo","description":"Multi-model deliberation over MCP: full responses plus typed cross-model reactions from other labs.","version":"1.2.0","publisher":{"kind":"domain","id":"mumo.chat","label":"mumo.chat","url":"https://mumo.chat"},"website":"https://mumo.chat/install","repository":"https://github.com/mumo-chat/mumo-mcp","remotes":[{"type":"streamable-http","url":"https://mumo.chat/api/mcp","headers":[{"description":"mumo platform API key as a bearer token. Create one at https://mumo.chat/settings/api-keys (keys begin with mmo_live_).","isRequired":true,"value":"Bearer {MUMO_API_KEY}","isSecret":true,"variables":{"MUMO_API_KEY":{"description":"mumo platform API key (mmo_live_…)","isRequired":true,"isSecret":true}},"name":"Authorization"}]}],"packages":[],"published":"2026-11-19","updated":"2026-11-19","status":"online","auth":"","latency_ms":1002,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"create_deliberation","title":"Start a deliberation","description":"Start a multi-model AI deliberation on a question or decision.\n\nRuns the prompt through multiple frontier AI models in parallel and extracts typed reactions (KEEP/EXPLORE/CHALLENGE/CORE/SHIFT) into a claim map of where they agree and diverge.\n\n**Returns immediately (async).** The response is a compact ack — `{ session_id, round_id, round_index, status: 'processing', progress_url, ... }` — NOT the ","read_only":false},{"name":"ask_a_model","title":"Ask one model","description":"Put a question to ONE model of your choice and get its answer. Use it for a single outside opinion from another lab's model.\n\nThis is not a deliberation: there are no other models, so there are no cross-model reactions and no claim map. For structured disagreement between 2–3 models, use `create_deliberation` instead.\n\n**Returns immediately (async).** The response is a compact ack — `{ session_id,","read_only":false},{"name":"append_round","title":"Add a follow-up round","description":"Add a follow-up round to an existing deliberation session.\n\nUse after reading the previous round's claim_map and responses to steer the conversation. The `snippets` array lets you forward specific quotes from the prior round's responses with a typed reaction:\n- KEEP: this point is strong, preserve it\n- EXPLORE: dig deeper on this thread\n- CHALLENGE: push back on this claim\n- CORE: this is load-bea","read_only":false},{"name":"wait_for_round","title":"Wait for a round to finish","description":"Wait for a deliberation round to finish, then return the full session.\n\nThis is the agent-friendly follow-up to `create_deliberation` and `append_round`: those tools return a fast ack; this tool polls the lightweight progress endpoint internally and fetches the full transcript only once terminal state is reached.\n\nUse this instead of repeatedly calling `get_session` while models are running.\n\nThe ","read_only":true},{"name":"get_session","title":"Read a session","description":"Fetch the full state of a deliberation session including all rounds, responses, snippets, and claim maps.\n\nUse to re-read completed session state. While a round is running, prefer `wait_for_round` so you do not repeatedly fetch the full transcript.\n\nThe claim_map on each round is the highest-signal representation: shows which claims multiple models reacted to, who originated them, and what each re","read_only":true},{"name":"list_sessions","title":"List your sessions","description":"List the caller's deliberation sessions, optionally filtered by status.\n\nMost useful for agents managing multiple concurrent sessions — use `status: 'ready'` to find sessions awaiting your next round. Returns a lightweight list (no response bodies); call `get_session` for full content.","read_only":true},{"name":"list_models","title":"List available models","description":"List the full model catalog. Returns id, provider, display name, context window, max output tokens, pricing, and a per-model `available` verdict for your account (with `unavailable_reason` when false). Nothing is filtered out — `available` is what varies by caller.\n\nCall before `create_deliberation` if the user wants specific models. Model IDs from this endpoint are what `create_deliberation`'s `m","read_only":true},{"name":"share_session","title":"Share a session","description":"Share a deliberation session at a public URL — anyone with the link can view it in the read-only reader deck.\n\nReturns the public `share_url` plus two machine-readable twins: `markdown_url` (the full transcript with per-round claim maps — the review/audit surface) and `brief_url` (synthesis-only triage tier, ~1-2k tokens). Hand the markdown twin to a reviewer model, or the share_url to a human — n","read_only":false},{"name":"get_credit","title":"Read credit balance","description":"Fetch the caller's current credit wallet balance.\n\nReturns `effective_balance_usd` (markup-included, what's left to spend). At or below zero, every new round is refused until top-up or the monthly free-credit reset. Above zero, a round is admitted when the balance also covers that round's minimum (each model's reserved output plus input and the post-round reactions/takeaway) — a per-request check,","read_only":true}],"server_info":{"name":"mumo","version":"1.2.0"},"category":"agents","tags":[],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-09-08","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/chat-mumo-mcp/"}