Rigol DHO oscilloscope through rigol-dho-mcp (controlled MCP contract)

Install

Three ways to run this device. Each one serves its fake backend: no instrument, no simulator install and no upstream checkout.

openai4s lab add labs/mattjax16__rigol-dho-mcp

git clone --depth 1 https://github.com/PKU-YuanGroup/OpenMHS.git && cd OpenMHS
PYTHONPATH=MHS/sdk/src python3 -m mhs serve labs/mattjax16__rigol-dho-mcp --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

{
  "mcpServers": {
    "rigol-dho-mcp": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/mattjax16__rigol-dho-mcp",
        "--mcp"
      ],
      "env": {
        "PYTHONPATH": "/path/to/OpenMHS/MHS/sdk/src"
      }
    }
  }
}

What it does

Actions

identify

Query the *IDN? identity string through the identify tool.

get_status

Read trigger status, sample rate, memory depth, acquisition type, timebase and enabled-channel settings, as the strings the scope returns.

run_control

Send one acquisition control (run, stop, single, autoset, clear, force_trigger); the reply carries the queried trigger status.

configure_channel

Change only the supplied analog-channel settings; returns the queried channel settings (no inversion readback).

configure_timebase

Set the main timebase scale and/or offset; returns the queried values.

configure_trigger_edge

Set EDGE trigger mode, then the supplied source, slope, level and sweep; returns the queried trigger settings and status.

configure_acquisition

Set memory depth, acquisition type and average count; returns the queried values and sample rate.

configure_cursors

Set the cursor mode (OFF, MANual, TRACk) with type and source or track sources; returns the queried mode. Coordinates use the typed cursor bindings.

get_cursor_values

Read cursor positions and deltas of the active mode; the complete result is a JSON artifact.

get_measurement

Select and read one automatic measurement item on one channel (SI units); selecting is a scope write.

measure_between

Select and read a delay (s) or phase (degrees) item between two channels; selecting is a scope write.

get_waveform

Capture the screen or deep-memory waveform: statistics plus every returned decimated time/voltage sample, as a JSON artifact. Memory mode needs a fresh STOP status first.

get_screenshot

Capture the scope display as a PNG image artifact.

configure_cursors_time

Manual TIME cursors: sets type TIME and cursor A/B coordinates in seconds.

configure_cursors_amplitude

Manual AMPLitude cursors: sets type AMPLitude and cursor A/B coordinates in volts.

configure_cursors_current

Manual cursors on the retained type: enters MANual, reads the type, applies only that axis's candidates and omits cursor_type. An unreadable type leaves the mode change unresolved.

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:

# 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/mattjax16__rigol-dho-mcp
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

mattjax16/rigol-dho-mcp

Pinned commit

f9ac71918698

Licence

MIT

Stars

2

Evidence

contract_checked on the fake backend

Backends

fake, hardware

The driver package MHS/drivers/labs/mattjax16__rigol-dho-mcp wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.