Labs · Electronics and measurement

Siglent SPD3303 series power supply (instro.psu.drivers.siglent_spd3303.SiglentSPD3303)

Siglent SPD3303 series power supply (instro.psu.drivers.siglent_spd3303.SiglentSPD3303), adapted from nominal-io/instro. It reads voltage_ch1, current_ch1, regulation_mode_ch1, voltage_ch2 and 3 more; sets voltage_setpoint_ch1, current_setpoint_ch1, output_enabled_ch1, voltage_setpoint_ch2 and 2 more; runs output_off. output_off: disable both channel outputs (OUTP CH1,OFF and OUTP CH2,OFF); it takes no input and is the declared safe state. A hardware driver: the market serves its fake backend, so no instrument is needed.

hardwareRisk R1Apache-2.0contract_checkedserved on the fake backend
openai4s lab add labs/nominal-io__instro

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/nominal-io__instro

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/nominal-io__instro --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": {
    "instro": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/nominal-io__instro",
        "--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

  • voltage_ch1
  • current_ch1
  • regulation_mode_ch1
  • voltage_ch2
  • current_ch2
  • regulation_mode_ch2
  • psu_mode

Adjusts

  • voltage_setpoint_ch1
  • current_setpoint_ch1
  • output_enabled_ch1
  • voltage_setpoint_ch2
  • current_setpoint_ch2
  • output_enabled_ch2

Actions

output_off
Disable both channel outputs (OUTP CH1,OFF and OUTP CH2,OFF); it takes no input and is the declared safe state

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/nominal-io__instro
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
311aee4ae227
Licence
Apache-2.0
Stars
718
Evidence
contract_checked on the fake backend
Backends
fake, hardware

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