Siglent SDS2000X Plus through lxkang00/oscilloscope-mcp (SCPI transport) — 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/lxkang00__oscilloscope-mcp

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/lxkang00__oscilloscope-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

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": {
    "oscilloscope-mcp": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "labs/lxkang00__oscilloscope-mcp",
        "--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
trigger_status
acquisition_state

Adjusts

Nothing declared.

Actions

acquisition_control: Send one acquisition control: run, stop, autoset, force trigger, clear measurement statistics or factory reset. The driver sends the same SCPI word the pinned handler sends.
configure_channel: Set analog channel settings with the pinned :CHANnelN: commands; reply is the handler summary.
get_channel: Read the eight settings the pinned get_channel handler reads. A native failure is reported as a failed call instead of being hidden behind the handler's N/A fallback.
configure_timebase: Set main timebase scale, delay and mode under :TIMebase:.
get_timebase: Read timebase scale, delay and mode.
configure_trigger: Set trigger sweep, type, source, level, slope, coupling and holdoff in the pinned order.
get_trigger: Read the current trigger type, sweep, source, level and slope.
configure_acquisition: Set acquisition mode, memory depth, interpolation and average count under :ACQuire:.
get_acquisition: Read acquisition mode, memory depth, sample rate and interpolation.
measure: Select and read one automatic measurement item. The reply is the pinned handler's text; the numeric value is parsed from the same reply and is null when it is not a number.
get_measure_stats: Read count, mean, minimum, maximum and standard deviation of the measurement statistics.
get_waveform_preamble: Read and parse the ten-field waveform preamble. The waveform sample array is not carried by this binding.
configure_display: Set display grid, persistence, intensity, grid style and axis mode.
configure_cursors: Set cursor mode, sources and manual cursor type.
get_cursor_values: Read cursor mode and, when cursors are on, delta X and delta Y.
configure_math: Set math display, function, sources, scale, offset and FFT options.
configure_digital: Set digital-bus display, position, height, label and threshold on MSO models.
save_setup: Save the current setup to internal memory or USB with the pinned filename validation.
recall_setup: Recall a saved setup from internal memory or USB with the pinned filename validation.
get_frequency_counter: Read the hardware frequency counter mode, source and current frequency.
get_status: Read acquisition state, trigger state, operation complete and event status register.
get_next_error: Read and clear the next device error-queue entry.

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/lxkang00__oscilloscope-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: lxkang00/oscilloscope-mcp
Pinned commit: 3eebcdfb3c33
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/lxkang00__oscilloscope-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.