LeCroy Oscilloscope MCP
Enables remote control of LeCroy oscilloscopes via SCPI commands over LAN to perform waveform capture, screenshots, measurements, channel configuration, and triggering through natural language. Supports multiple LeCroy models including WaveSurfer, HDO, WaveRunner, and WavePro series with automatic model detection.
README
lecroy-mcp
MCP server for controlling LeCroy oscilloscopes via SCPI over LAN (VXI-11) or USB.
Requirements
- uv installed
- A LeCroy oscilloscope connected over LAN or USB
MCP configuration
Add to your MCP client config (e.g. Claude Code's .mcp.json):
{
"mcpServers": {
"lecroy-scope": {
"type": "stdio",
"command": "uvx",
"args": ["lecroy-mcp"]
}
}
}
uvx will automatically download and run the server — no manual installation needed.
Connection options
Option 1 — Pre-configure the IP address (recommended for LAN)
Set LECROY_HOST in the env block and the server auto-connects on startup:
"env": {
"LECROY_HOST": "192.168.1.111"
}
Option 2 — Pre-configure a full resource string (LAN or USB)
Use LECROY_RESOURCE for full control, including USB connections:
"env": {
"LECROY_RESOURCE": "USB0::0x05FF::0x1023::12345::INSTR"
}
Option 3 — Manual connection
Leave out the env block and connect from within the MCP session:
scope_scan— auto-detect LeCroy scopes on the local networkscope_list_resources— list all VISA resources (LAN + USB)scope_connect("TCPIP0::192.168.1.111::inst0::INSTR")— connect directly
Optionally set LECROY_SUBNET to hint the scan range:
"env": {
"LECROY_SUBNET": "192.168.1.0/24"
}
Usage
Once connected, you have tools for:
- Channel setup (scale, offset, coupling, bandwidth limit)
- Trigger configuration (mode, source, level, edge)
- Timebase and memory depth
- Automated measurements (PKPK, FREQ, RMS, RISE, DUTY, etc.)
- Waveform capture (JSON or CSV)
- Screenshots
- Math functions (FFT, INTG, DIFF, etc.)
- WaveSource built-in generator (WaveSurfer 3000Z and similar)
Supported models
The server detects the connected model and adjusts commands accordingly. Profiles are included for:
- WaveSurfer 3000Z / 4000HD
- HDO4000A / HDO6000B / HDO8000A
- WaveRunner 6000 / 8000
- WavePro HD
- MDA800A, SDA
Unknown models fall back to conservative defaults.
Updating
With uvx, use the @latest tag to force the newest version:
uvx lecroy-mcp@latest
Or update the args in your .mcp.json to always pull the latest:
"args": ["lecroy-mcp@latest"]
With pip:
pip install --upgrade lecroy-mcp
Manual installation
If you prefer not to use uvx:
pip install lecroy-mcp
Then use lecroy-mcp as the command in your MCP config instead of uvx lecroy-mcp.
Notes
- Requires
pyvisa-pybackend — NI-VISA is currently not supported (breaks screenshot capture) - All VISA access is serialized via a threading lock; parallel MCP tool calls are safe
Troubleshooting
Diagnostic messages not appearing in MCP logs
If you are not seeing server log output (e.g. auto-connect status or errors) in your MCP client's log viewer, add PYTHONUNBUFFERED to the env block:
"env": {
"PYTHONUNBUFFERED": "1"
}
This disables Python's output buffering so log messages are flushed immediately. It is not required for normal operation.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.