Care-O-bot Gazebo simulation scene — device market

Install

Three ways to run this device. Each one serves its fake backend: no instrument, no simulator install and no upstream checkout.

OpenAI4S (one command)

shell

openai4s lab add robots/ipa320__cob_simulation

Installs the device into the OpenAI4S Lab on its fake backend and starts it. First time? See setup below.

Or, in the workbench, open the Lab tab → Market → Install.

Standalone MHS endpoint

shell

git clone --depth 1 https://github.com/PKU-YuanGroup/OpenMHS.git && cd OpenMHS
PYTHONPATH=MHS/sdk/src python3 -m mhs serve robots/ipa320__cob_simulation --port 7400
# in a second terminal, from the same directory:
PYTHONPATH=MHS/sdk/src python3 -m mhs describe --endpoint http://127.0.0.1:7400

Serves the device as an MHS endpoint on port 7400 from an OpenMHS clone (Python 3.10 or later, standard library only); describe prints what it offers.

Any MCP host (Claude Desktop, Cursor, …)

mcp configuration

{
  "mcpServers": {
    "cob-simulation": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "robots/ipa320__cob_simulation",
        "--mcp"
      ],
      "env": {
        "PYTHONPATH": "/path/to/OpenMHS/MHS/sdk/src"
      }
    }
  }
}

Add this server to the host's MCP configuration and replace /path/to/OpenMHS with the path of your OpenMHS clone. The host starts the server and talks to it on stdin and stdout.

What it does

Measures

model_names
robot_pose

Adjusts

Nothing declared.

Actions

delete_model: Call the acknowledged gazebo_msgs/DeleteModel service to remove one model from the running Gazebo world; the output is the service's own success and status text
publish_model_state: Publish one gazebo_msgs/ModelState on /gazebo/set_model_state with the same fields the move tool publishes; the receipt confirms rosbridge transmission only, not that Gazebo moved the model or reached the pose

Names as the driver declares them. Units, limits and the safety declaration are in the package's REFERENCE.md.

First-time setup

The OpenAI4S workbench with the OpenMHS lab, from a source checkout:

shell

# OpenAI4S workbench with the OpenMHS lab (source checkout)
git clone --recursive https://github.com/PKU-YuanGroup/OpenAI4S.git
cd OpenAI4S && ./setup.sh && source .venv/bin/activate
openai4s lab add robots/ipa320__cob_simulation
openai4s serve        # open the Lab tab

The standalone endpoint and the MCP server need only an OpenMHS clone and Python 3.10 or later. More in the market's getting-started guide and on the OpenAI4S host page.

Source and evidence

Upstream: ipa320/cob_simulation
Pinned commit: 907144342c03
Licence: Apache-2.0
Stars: 73
Evidence: contract_checked on the fake backend
Backends: fake

The driver package MHS/drivers/robots/ipa320__cob_simulation wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.