Install mumo in Hermes Agent.

Install the mumo skill

The skill is what teaches Hermes how to actually use mumo — when to invoke a panel, the deliberation loop, how to read claim maps, how to verify a session was actually created. Without it, you get tools without a manual, and the agent will guess.

Clone mumo-hermes into your Hermes skills directory:

git clone https://github.com/mumo-chat/mumo-hermes \
  ~/.hermes/skills/autonomous-ai-agents/mumo

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.

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 Hermes' config in the next step.

Add mumo to Hermes config

Hermes reads MCP servers from ~/.hermes/config.yaml under mcp_servers. Merge this block (or merge under an existing mcp_servers: if you have one), replacing the placeholder with your key:

mcp_servers:
  mumo:
    url: "https://mumo.chat/api/mcp"
    headers:
      Authorization: "Bearer mmo_live_YOUR_KEY_HERE"
    tools:
      include:
        - create_deliberation
        - wait_for_round
        - append_round
        - get_session
        - list_sessions
        - list_models
        - get_credit
      resources: false
      prompts: false

The same YAML ships in the cloned repo at config/mumo.yaml for copy-paste. The tools.includeallowlist scopes mumo to its seven tools so the agent's tool surface stays focused.

Restart Hermes

Fully exit and restart Hermes so it picks up both the new skill and the new MCP server. The /reload-mcp slash command works for some installs but not all — restart is the canonical step.

After restart, the agent should expose the seven mumo tools (visible as mcp_mumo_create_deliberation, mcp_mumo_wait_for_round, etc.) and load the mumo skill into its skill registry.

Run your first deliberation

Name mumo explicitly the first time so Hermes 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 list_sessions or check mumo.chat. The skill teaches this discipline; this is the user-facing reminder.