Rohde & Schwarz NGMO2 channel A — 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/eta-systems__labor-gpib

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/eta-systems__labor-gpib --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": {
    "labor-gpib": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/eta-systems__labor-gpib",
        "--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

identity
status_byte

Adjusts

voltage_setpoint
current_limit
measurement_interval
averaging_samples
output_enabled
sense_function
current_range
output_format
display_enabled

Actions

measure_voltage: Measure a DC or RMS voltage on a declared channel or terminal pair and return the value with its sampling timestamp and measurement range.
measure_current: Measure current on a declared channel and return the value with its timestamp and range.
output_off: Send :OUT:A OFF: the safe state, with no input and no read-back wait
scpi_rst: Call device.reset (src/devices/rohde_schwarz_ngmo2.py:85-86). rst writes *RST (lines 81-83) and cls writes *CLS (lines 30-31). The comment on rst says this returns the supply to the *RST default conditions and does not state the output, the voltage, the current or the averaging. An ordinary command: the safety reset does not call it, and it is not a re-enable or a safe-state action. The three cached set points are refused before device.reset is called, including when that call raises, until this driver writes them. The operator confirms the instrument, including whether an output is enabled.

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/eta-systems__labor-gpib
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: eta-systems/labor-gpib
Pinned commit: d5fe1b230344
Licence: NOASSERTION
Stars: 2
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/eta-systems__labor-gpib wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.