OpenMHSindependent draft 0.9
Playground
Open menu

Labs · Liquid handling and fluidics

Opentrons OT-2 liquid handler (ot2_interface.OT2_Driver)

Opentrons OT-2 liquid handler (ot2_interface.OT2_Driver), adapted from ad-sdl/ot2_module. It reads robot_status, runs, active_run_id and active_run_status; runs start_protocol and stop_active_run. start_protocol: upload an Opentrons protocol file that the operator overlay allows, create a run and send the robot's play action; the run continues on the robot after this action returns, until it ends or is stopped, and the protocol alone decides what the robot does in it. A hardware driver: the market serves its fake backend, so no instrument is needed.

hardwareRisk R2MITcontract_checkedserved on the fake backend
openai4s lab add labs/ad-sdl__ot2_module
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/ad-sdl__ot2_module

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/ad-sdl__ot2_module --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": {
    "ot2-module": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/ad-sdl__ot2_module",
        "--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

  • robot_status
  • runs
  • active_run_id
  • active_run_status

Adjusts

Nothing declared.

Actions

start_protocol
Upload an Opentrons protocol file that the operator overlay allows, create a run and send the robot's play action; the run continues on the robot after this action returns, until it ends or is stopped, and the protocol alone decides what the robot does in it
stop_active_run
Send the robot's run stop action to every run it lists as running, paused, finishing or in a status the clone does not name, and to a run of this driver whose play may be in flight, and confirm each by a fresh read; it takes no input

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/ad-sdl__ot2_module
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
39ffdfdb73c3
Licence
MIT
Stars
1
Evidence
contract_checked on the fake backend
Backends
fake, hardware

The driver package MHS/drivers/labs/ad-sdl__ot2_module wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.