Uthira SCARA/RRP robot simulation — 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/uthiras__scara_robot_ros2

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/uthiras__scara_robot_ros2 --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": {
    "scara-robot-ros2": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "robots/uthiras__scara_robot_ros2",
        "--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

read_joint_states
read_forward_kinematics_matrix

Adjusts

Nothing declared.

Actions

command_joint_efforts: Publish one three-element joint effort command on the controller's command topic; the receipt confirms only that rosbridge accepted the publication and reports the efforts sent, not that a controller applied them, that the arm moved, or that it can stop. After an e-stop and reset the world stays paused, and a command sent then acts only when the operator unpauses it
forward_velocity_kinematics: Call the observational Forward_Velocity_Kinematics service and return its end-effector velocity values; the service computes from the last joint state and does not command motion

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/uthiras__scara_robot_ros2
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: uthiras/scara_robot_ros2
Pinned commit: ece3e91727b0
Licence: NOASSERTION
Stars: 11
Evidence: contract_checked on the fake backend
Backends: fake

The upstream repository asserts no licence (NOASSERTION); check it before you redistribute the upstream code.

The driver package MHS/drivers/robots/uthiras__scara_robot_ros2 wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.