Install mumo in OpenClaw.

Generate your API key

Sign in, create a mumo API key, and copy the value that starts with mmo_live_. You'll paste it into OpenClaw's MCP config in the next step.

Register the mumo MCP server

OpenClaw stores outbound MCP servers in ~/.openclaw/openclaw.json under mcp.servers.<name>. Use the CLI to register mumo, replacing the placeholder with your real key:

openclaw mcp set mumo '{
  "url": "https://mumo.chat/api/mcp",
  "transport": "streamable-http",
  "headers": {
    "Authorization": "Bearer mmo_live_YOUR_KEY_HERE"
  }
}'

Verify the registration landed:

openclaw mcp list
openclaw mcp show mumo

The Authorization header is a literal Bearer string — OpenClaw's MCP client doesn't support env-var pointers for HTTP headers. If you rotate your key, re-run openclaw mcp set mumo with the new value.

Install the mumo skill

Registering the MCP server gives the agent the tools, but not the discipline to use them well. The skill teaches OpenClaw the deliberation loop, claim-map reading, snippet doctrine, and how to verify a session was actually created. Without it, the agent has tools without a manual.

The fastest path is via ClawHub, OpenClaw's skill registry:

openclaw skills install mumo

That pulls mumo from ClawHub and lands it at ~/.openclaw/skills/mumo/.

If you'd rather track the source repo directly (e.g., to pull main ahead of registry releases), clone instead:

git clone https://github.com/mumo-chat/mumo-openclaw \
  ~/.openclaw/skills/mumo

Either way, the skill ships the canonical SKILL.md, four cognitive-shape playbooks (contested decision, design review, uncertainty expansion, red team), and reference docs for claim-map reading, snippet doctrine, model selection, and synthesis.

Restart OpenClaw

Fully exit and restart OpenClaw so it picks up both the new MCP server registration and the new skill. The coding and messagingtool profiles expose configured MCP servers by default; if you're on the minimal profile, MCP tools stay hidden.

After restart, the seven mumo tools surface as mumo__create_deliberation, mumo__wait_for_round, mumo__append_round, mumo__get_session, mumo__list_sessions, mumo__list_models, mumo__get_credit (OpenClaw uses the <server>__<tool> double-underscore convention).

Verify the skill loaded

In your OpenClaw session, run:

/skill mumo

You should see the mumo skill listed as ready with the description starting "Multi-model deliberation via mumo's MCP server…".

Run your first deliberation

Name mumo explicitly the first time so OpenClaw routes through the panel. The skill will guide the agent through the create→wait→read→snippet loop and teach it to verify the session actually fired.

Ask mumo to compare Postgres and MongoDB for our event store.
Include the constraints from this repo and tell me where the models disagree.

If the agent claims a deliberation succeeded but doesn't produce a UUID-format session ID, the call didn't fire — confirm with mumo__list_sessions or check mumo.chat. The skill teaches this discipline; this is the user-facing reminder.