OpenMHSindependent draft 0.9
Playground
Open menu

Labs · Robot arms and grippers

OpenLH liquid handler (uArm Swift Pro)

OpenLH liquid handler (uArm Swift Pro), adapted from idc-milab/openlh. It reads position_x, position_y, position_z, polar_rotation and 5 more; sets base_angle, left_angle, right_angle, hand_angle and 2 more; runs move_to_position and tool_off. move_to_position: move the tool centre point to a Cartesian position and orientation in a named frame. The endpoint solves inverse kinematics; an unreachable target is rejected before motion. A hardware driver: the market serves its fake backend, so no instrument is needed.

hardwareRisk R2licence not assertedcontract_checkedserved on the fake backend
openai4s lab add labs/idc-milab__openlh
All install options REFERENCE.md Upstream repository Registry record

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 labs/idc-milab__openlh

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 labs/idc-milab__openlh --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": {
    "openlh": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/idc-milab__openlh",
        "--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

  • position_x
  • position_y
  • position_z
  • polar_rotation
  • polar_stretch
  • polar_height
  • ultrasonic_distance
  • limit_switch
  • is_moving

Adjusts

  • base_angle
  • left_angle
  • right_angle
  • hand_angle
  • pump_on
  • gripper_closed

Actions

move_to_position
Move the tool centre point to a Cartesian position and orientation in a named frame. The endpoint solves inverse kinematics; an unreachable target is rejected before motion.
tool_off
Turn the pump and the gripper off; this is the declared safe state because the upstream API has no motion halt

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 labs/idc-milab__openlh
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

Pinned commit
6a7562c61656
Licence
NOASSERTION
Stars
27
Evidence
contract_checked on the fake backend
Backends
fake, hardware

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

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