Logic Analyzer
FreeNot checkedAI-driven USB logic analyzer control via FastMCP. Captures digital traces, decodes UART/I2C/SPI, and exports VCD for PulseView, supporting sigrok hardware and b
About
AI-driven USB logic analyzer control via FastMCP. Captures digital traces, decodes UART/I2C/SPI, and exports VCD for PulseView, supporting sigrok hardware and built-in simulator.
README
MIT License Python 3.12+ FastMCP 3.2+
AI-driven USB logic analyzer control via FastMCP 3.2. Capture digital traces with sigrok or the built-in simulator, decode UART/I2C/SPI, and export VCD for PulseView.
How it runs
| Mode | Hardware | When |
|---|---|---|
| Simulator (default) | None | Development, CI, agent dry-runs |
| sigrok | Hantek 6022BL (LA mode), DSLogic, FX2 clones | Production bench with sigrok-cli |
The MCP server does not bundle sigrok. Install PulseView or sigrok-cli separately, then connect your USB LA.
Hands-in / Hands-out
| Direction | Artifacts | Notes |
|---|---|---|
| Hands-in | device_id, channels, trigger |
Via la_device, la_configure, la_trigger |
| Hands-out | Trace preview (downsampled JSON) | la_capture(operation="single") |
| Hands-out | CSV, VCD, JSON summary | la_capture(operation="export_vcd") in LOGIC_ANALYZER_MCP_CAPTURE_DIR |
| Hands-out | Protocol decode rows | la_decode(operation="uart") |
Fleet pipelines
| Partner MCP | Workflow |
|---|---|
| oscilloscope-mcp | Mixed-signal bring-up (analog + digital) |
| kicad-mcp | Verify SPI/I2C after PCB bring-up |
| chip-design-mcp | Debug FPGA/MCU buses |
Bench family
One bench, nine servers. bench-orchestrator-mcp conducts (mcu_bringup drives
its six wired peers); the rest are instruments:
| Server | Role | Wired peer? |
|---|---|---|
| bench-orchestrator-mcp | Conductor — bench_workflow (power_check, bus_check, debug_check, mcu_bringup) |
— (it conducts) |
| jtag-swd-mcp | Halt / inspect / flash the CPU | yes (dbg) |
| oscilloscope-mcp | Scope traces — signal integrity | yes (scope) |
logic-analyzer-mcp (here) |
Digital capture + UART/I2C/SPI decode | yes (la) |
| multimeter-mcp | DMM — rails, continuity | yes (dmm) |
| power-supply-mcp | Bench PSU — target power | yes (psu) |
| function-generator-mcp | AWG stimulus — clocks, reset, fault injection | yes (fgen) |
| bench-camera-mcp | Bench vision — LEDs, 7-segment | family (not wired) |
| spectrum-analyzer-mcp | Spectrum — EMI around the target | family (not wired) |
Quick Start
Set-Location D:\Dev\repos\logic-analyzer-mcp
uv sync --extra dev
just webapp
# Open http://127.0.0.1:10989
STDIO-only (Cursor MCP):
just serve
Dry-run without hardware:
la_device(operation="connect", device_id="sim-la-001")
la_capture(operation="single", sample_rate_hz=1000000, sample_count=4096)
la_decode(operation="uart", rx="D0")
Cursor MCP config
Add to C:\Users\sandr\.cursor\mcp.json:
"logic-analyzer-mcp": {
"command": "C:/Users/sandr/.local/bin/uv.exe",
"args": [
"--directory",
"D:/Dev/repos/logic-analyzer-mcp",
"run",
"python",
"-m",
"logic_analyzer_mcp",
"--stdio"
],
"env": {
"FASTMCP_BANNER": "0",
"FASTMCP_UPDATE_CHECK": "0",
"PYTHONUNBUFFERED": "1",
"LOGIC_ANALYZER_MCP_BACKEND": "auto"
}
}
Restart Cursor after editing mcp.json.
Tools
| Tool | Operations |
|---|---|
la_device |
list, connect, disconnect, status, capabilities, backends |
la_configure |
channels, sample_rate, get, simulator_pattern |
la_trigger |
set, get |
la_capture |
single, preview, export_csv, export_vcd, export_summary, last |
la_decode |
list, run, last, uart, i2c, spi |
la_help |
discover, tool_help, status, quickstart, faq, hardware_guide |
Webapp
| Port | Role |
|---|---|
| 10985 | Backend (FastAPI + MCP /mcp) |
| 10989 | Frontend (Vite React — dashboard, device, configure, trigger, trace, decode, logs) |
just webapp
Native App (Tauri)
A Tauri 2.0 wrapper (native/) packages the backend with PyInstaller into a single NSIS installer — one shortcut, embedded Python, no separate runtime.
pwsh -NoProfile -File native/build.ps1 # webapp → PyInstaller → Rust → NSIS
just cua-nsis-test # install → launch → verify → uninstall
Documentation
- INSTALL.md — setup paths
- docs/ARCHITECTURE.md — system design
- docs/TOOLS.md — portmanteau reference
- docs/HARDWARE.md — LA buying guide
- docs/BACKENDS.md — sigrok + simulator
- llms.txt — agent discovery index
License
MIT — see LICENSE.
Installing Logic Analyzer
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/sandraschi/logic-analyzer-mcpFAQ
Is Logic Analyzer MCP free?
Yes, Logic Analyzer MCP is free — one-click install via Unyly at no cost.
Does Logic Analyzer need an API key?
No, Logic Analyzer runs without API keys or environment variables.
Is Logic Analyzer hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Logic Analyzer in Claude Desktop, Claude Code or Cursor?
Open Logic Analyzer on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Opencode Omniroute Plugin
OpenCode plugin for the OmniRoute AI Gateway. Drives dynamic model discovery, /connect auth flow, and multi-instance OmniRoute providers via the official @openc
by GitHub ActionsRoblox Studio
Enables AI coding tools to control Roblox Studio for workspace exploration, instance manipulation, and script management. It provides tools for playtesting, sce
by paralovAntigravity Drawio
MCP server that enables AI assistants to create, parse, render, and validate Draw.io diagrams programmatically.
by S-SUJAN-SFetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
by lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
Compare Logic Analyzer with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
