Opentrons OT-2 (HTTP wrapper) — 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 labs/steiva__opentrons-ot2-http-python-wrapper

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/steiva__opentrons-ot2-http-python-wrapper --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": {
    "opentrons-ot2-http-python-wrapper": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/steiva__opentrons-ot2-http-python-wrapper",
        "--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_model
run_count

Adjusts

Nothing declared.

Actions

aspirate: Draw a specified volume of liquid from a declared labware well into a pipette tip, with a bounded flow rate and an optional liquid-level offset.
dispense: Dispense a specified volume from the pipette into a declared labware well, with optional blowout and mixing after dispense.
create_run: Create a run on the robot; needed before pipette, labware, movement and fluid commands
load_pipette: Load the configured pipette on a mount
load_labware: Load labware into a deck slot
home: Home the robot gantry
control_run: Play, pause, stop or recover the current run
stop_run: Stop the current run (the safe-state action); 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/steiva__opentrons-ot2-http-python-wrapper
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: steiva/opentrons-ot2-http-python-wrapper
Pinned commit: 6bf929c11fe9
Licence: NOASSERTION
Stars: 0
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/steiva__opentrons-ot2-http-python-wrapper wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.