By yoelbassin
Control RF hardware and GNU Radio flowgraphs through natural language — survey spectrum, build and run receivers, simulate RF scenes, and run closed-loop TX/RX experiments, all while leaving a reproducible project behind.
Use when the user wants to receive or demodulate a specific signal — build, validate, run, and verify a receiver pipeline, then save it as a reusable, GRC-openable flowgraph.
Use when a receiver runs but produces no output, noise, or the wrong result — systematically locate the fault instead of guessing, using render and measure to see the problem.
Use ONLY as a last resort when no Marconi tool or vocabulary block can express the task — write a Python script against the marconi library, run it, and report the capability gap.
Use when the user wants a test signal or a simulated RF environment with no hardware — translate intent into a scene and register it as a persistent simulated device.
Use when the user wants to know what signals are present — characterize a capture or a simulated device's spectrum (PSD, signal detection, spectrogram) and summarize what's on the air.
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
o)))
|
.-------.
| o o |
| v |
'-------'
Hi! I'm Marco.
LLM-driven RF for Claude Code. Describe what you want on the air and I survey the
spectrum, build and run the receiver, look at the signal, and leave a reproducible
RF project behind — SigMF captures, YAML pipelines, and .grc flowgraphs you own.
Early development — v1.0 is simulation-only (no hardware yet). See
ROADMAP.md.
Proviously known as GNURadio/GR-MCP.
uv and Python ≥ 3.13In Claude Code:
/plugin marketplace add yoelbassin/gr-mcp
/plugin install marconi
That's it — uv starts the MCP server on first use and loads the skills. Nothing
else to configure.
Ask in plain language:
"Simulate an FM station at 100.3 MHz and build me a receiver."
"Here's a capture,
mystery.wav— survey what's on the air, then decode the strongest carrier."
I pick the right skill and drive the workflow end to end:
Artifacts land under artifacts/ in the server's working directory; set
MARCONI_WORKSPACE to put them elsewhere.
npx claudepluginhub yoelbassin/gr-mcp --plugin marconiDrive Ansys HFSS / AEDT antenna and RF simulations via PyAEDT — env handshake, standard simulation pipeline, and ready-to-adapt templates for S-parameters, far-field patterns, and parametric sweeps.
AI-powered hardware development platform — design, verify, synthesize, and deploy working RTL with natural language. 18 agents, 25 skills, 8 IP blocks.
Node Hardware MCP - Comprehensive Hardware Monitoring and System Analysis for LLMs with real-time performance metrics
Domain-specific expert agents for research, documentation, and specialized tasks
Autonomous research orchestration: agents for hypothesis-driven investigation, experiment running, fresh-eyes review, and batch evaluation.
Build FastMCP 3.x Python MCP servers — covers provider/transform architecture (including CodeMode, Tool Search, and server-level transforms), component versioning, session state, authorization (MultiAuth, PropelAuth, connection-pooled token verifiers), evaluation creation, Pydantic validation, async patterns, STDIO and HTTP transports, nginx reverse proxy deployment, background tasks, Prefab Apps UI, security patterns, client SDK usage, testing, deployment, and migration from FastMCP v2. TypeScript is a legacy reference only and is not updated for v3.