§ Claude Code

Claude Code + ROBOT.md

Connect Claude Code to a ROBOT.md manifest so it can describe and safely operate your robot.

1. Install

Three commands. Each is copy-able.

# add the MCP server
claude mcp add robot-md npx -y robot-md-mcp
# verify it registered
claude mcp list
# in a Claude session, ask:
> read my ROBOT.md and describe the robot

2. First conversation

An example transcript with Claude reading your manifest:

user: read my ROBOT.md
claude: I see a ROBOT.md describing a 5-DOF arm.
        Capabilities: pick, place, calibrate.
        Safety: collision_check required before pick.

3. Skills walkthrough

The cookbook walks an agent through discovering, installing, and verifying capabilities end-to-end.

Open the cookbook →

4. Gateway integration

For physical actuation, add robot-md-gateway (Layer 3). The gateway enforces the safety contract declared in your manifest before any actuator call.

Compliance docs →

5. Troubleshooting

No ROBOT.md found
The MCP server walks the working directory upward. Ensure your CWD is at or below the robot project root.
MCP not registered
Re-run claude mcp add robot-md npx -y robot-md-mcp and confirm with claude mcp list.
Gateway connection refused
The gateway is a separate daemon; start it before invoking actuator capabilities.

Full troubleshooting on docs.robotmd.dev →

Next steps

Run the cookbook →

Read Bob's story →

01 — Wire it

Do the cookbook.

Install robot-md, author a ROBOT.md, register with RRF, run a skill, and walk away with a signed audit bundle. About ten minutes, end to end.

Open the cookbook →
02 — Read it

Understand the format.

The ROBOT.md spec defines every required and optional field, the RCAN protocol conformance rules, and the compliance packet filing requirements. Normative text, schema, and examples.

Read the spec →
03 — Want this managed?

Compliance-bot waitlist.

Give your robot repo to Compliance-bot and get back a signed FRIA + IFU + safety-benchmark + EU-register filing in one day. Powered by Anthropic Managed Agents.

Join the waitlist →
Where safety is actually enforced.
Physical safety is enforced at Layer 3 (robot-md-gateway) or Layer 4 (a runtime that embeds it, e.g., OpenCastor). Declaration alone (Layer 1) does not enforce safety. Agent host alone (Layer 2) is not the safety boundary. If a deployment lacks Layer 3, no safety claim attaches to it.