GNURadio MCP Server
@yoelbassin
About GNURadio MCP Server
MCP server for GNU Radio
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is GNURadio MCP Server?
GNURadio MCP Server (formerly GR-MCP, now called Marconi) is an LLM-driven RF tool for Claude Code. It lets you describe what you want on the air in plain language, then surveys the spectrum, builds and runs receivers, examines signals, and leaves behind reproducible RF projects (SigMF captures, YAML pipelines, .grc flowgraphs). It is currently simulation-only — no hardware support yet.
How to use GNURadio MCP Server?
Install it in Claude Code by running /plugin marketplace add yoelbassin/gr-mcp then /plugin install marconi. The uv tool starts the MCP server on first use with no further configuration. Ask in plain language, for example "Simulate an FM station at 100.3 MHz and build me a receiver." Artifacts are saved under artifacts/ in the server’s working directory, or can be redirected via the MARCONI_WORKSPACE environment variable.
Key features of GNURadio MCP Server
- Survey spectrum (PSD, signal detection, spectrogram)
- Simulate a registered device from a description
- Build, demodulate, validate, and run a receiver
- Debug when a receiver outputs no signal
- Closed-loop transmit-then-receive in simulation
- Escape hatch to direct Python library access
Use cases of GNURadio MCP Server
- Simulate a radio station and automatically build a matching receiver
- Analyze an existing IQ capture file to detect and decode signals
- Debug a receiver that produces no output
- Run reproducible RF experiments in simulation
FAQ from GNURadio MCP Server
What software dependencies does it require?
It requires uv, Python ≥ 3.13, and GNU Radio 3.10+ installed system-wide (via conda-forge, package manager, or Homebrew). Analyzing existing IQ files does not need GNU Radio.
Where are the generated artifacts stored?
Artifacts land under artifacts/ in the server’s working directory. You can set the MARCONI_WORKSPACE environment variable to place them elsewhere.
Does it support real hardware?
No — v1.0 is simulation-only. Hardware support is planned for future releases (see ROADMAP.md).
How is it installed in Claude Code?
Run /plugin marketplace add yoelbassin/gr-mcp then /plugin install marconi. The server starts automatically on first use.
Frequently asked questions
What software dependencies does it require?
It requires `uv`, Python ≥ 3.13, and GNU Radio 3.10+ installed system-wide (via conda-forge, package manager, or Homebrew). Analyzing existing IQ files does not need GNU Radio.
Where are the generated artifacts stored?
Artifacts land under `artifacts/` in the server’s working directory. You can set the `MARCONI_WORKSPACE` environment variable to place them elsewhere.
Does it support real hardware?
No — v1.0 is simulation-only. Hardware support is planned for future releases (see `ROADMAP.md`).
How is it installed in Claude Code?
Run `/plugin marketplace add yoelbassin/gr-mcp` then `/plugin install marconi`. The server starts automatically on first use.
Basic information
More Other MCP servers
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Mcp
browsermcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
Mobile Mcp
mobile-nextModel Context Protocol Server for Mobile Automation and Scraping (iOS, Android, Emulators, Simulators and Real Devices)
Maestro
mobile-dev-incPainless E2E Automation for Mobile and Web
XcodeBuildMCP
cameroncookeA Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
Comments