mcpField
M
mcp-sigrok

mcp-sigrok

Local
github.com/daedalusDeveloper Tools2Updated 28w ago

About mcp-sigrok

mcp-sigrok exposes sigrok-cli operations to MCP clients for logic-analyzer hardware workflows, including acquisition and protocol decoding. It is intended for users who need to inspect devices, capture samples, or process saved sessions through MCP tools.

Key features

  1. 01Scan for connected devices
  2. 02Inspect drivers and formats
  3. 03Capture hardware samples
  4. 04Load and decode capture files
  5. 05Configure drivers and inspect decoder docs

Use cases

  1. 01Find logic-analyzer devices and driver details
  2. 02Capture samples from selected channels
  3. 03Decode I2C data from a saved session

MCP support

It runs as an stdio MCP server and exposes sigrok-cli functionality through tools for device discovery, capture, file processing, and configuration.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"daedalus-mcp-sigrok": {
"command": "uvx",
"args": [
"mcp-sigrok"
]
}
}
}
Run commanduvx mcp-sigrok

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-sigrok0.1.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-sigrok — MCP server for sigrok-cli

PyPI Python

MCP server that exposes all functionality of sigrok-cli as MCP tools. sigrok-cli is a cross-platform command-line utility for the sigrok software suite, used for hardware initialization, acquisition, protocol decoding, and saving logic analyzer sessions.

Install

pip install mcp-sigrok

Requirements

  • sigrok-cli must be installed on the system
Installing sigrok-cli

Debian/Ubuntu:

sudo apt install sigrok-cli

macOS:

brew install sigrok-cli

From source:

git clone git://sigrok.org/sigrok-cli
cd sigrok-cli
./autogen.sh
./configure
make
sudo make install

Usage

As MCP Server
# Run as stdio MCP server
mcp-sigrok

Or configure in your MCP settings:

{
  "mcpServers": {
    "sigrok": {
      "command": "mcp-sigrok"
    }
  }
}
Python API
from mcp_sigrok import (
    check_sigrok_cli,
    get_version,
    list_drivers,
    scan_devices,
    capture_samples,
    load_input_file,
)

# Check if sigrok-cli is available
if cli_path := check_sigrok_cli():
    print(f"Found sigrok-cli at: {cli_path}")

# Get version info
info = get_version()

# List available drivers
drivers = list_drivers()

# Scan for devices
devices = scan_devices()

# Capture samples
result = capture_samples("fx2lafw", samples=1000)

MCP Tools

ToolDescription
versionGet sigrok-cli version info
list_supportedList all supported features
list_hardware_driversList available hardware drivers
list_input_file_formatsList supported input formats
list_output_file_formatsList supported output formats
list_protocol_decodersList available protocol decoders
scan_for_devicesScan for detectable devices
show_device_infoShow device info for a driver
captureCapture samples from hardware
capture_for_timeCapture data for duration
load_fileLoad and process input file
show_decoder_docsShow protocol decoder docs
set_configSet driver configuration

Examples

Capture from logic analyzer
# Capture 1000 samples from fx2lafw device
result = capture(
    driver="fx2lafw",
    samples=1000,
    channels="0-7",
    output_format="hex"
)
Decode I2C protocol
# Load capture file and decode I2C
result = load_file(
    input_file="capture.sr",
    protocol_decoders="i2c",
    output_file="decoded.txt"
)
Scan for devices
# Find available devices
devices = scan_for_devices()
for device in devices.get("devices", []):
    print(f"Found: {device}")

Development

git clone https://github.com/daedalus/mcp-sigrok.git
cd mcp-sigrok
pip install -e ".[test]"

# run tests
pytest

# format
ruff format src/ tests/

# lint
ruff check src/ tests/

# type check
mypy src/

mcp-name: io.github.daedalus/mcp-sigrok

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.