GR-MCP: A gnuradio

A modern MCP server for GNURadio enabling automated, AI-assisted creation and control of GNURadio flowgraphs.

python

20

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "yoelbassin-gr-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/gr-mcp",
        "run",
        "main.py"
      ]
    }
  }
}

GR-MCP provides a programmable MCP server for GNURadio, enabling automated, AI-assisted creation and control of GNURadio flowgraphs. You can drive flowgraph generation, manage experiments at scale, and integrate with automation workflows and language models to prototype SDR workflows quickly.

How to use

You use GR-MCP by running the local MCP server and connecting your MCP client (such as automation tools or AI assistants) to the server. The server exposes a programmatic interface that lets you create, modify, and execute GNURadio flowgraphs (.grc) files, manage their parameters, and orchestrate SDR workflows through code.

How to install

Prerequisites you need on your machine include Python 3.13 or newer, GNURadio installed on your system, and the UV runtime environment. You will also want a Git client to fetch the MCP server repository.

Follow these steps to set up GR-MCP locally and prepare the MCP server for use.

Clone the MCP server repository to your workspace.

git clone https://github.com/yoelbassin/gr-mcp

Install GNURadio according to your platform's instructions. This step is outside the scope of these commands but is required for the MCP server to operate.

Set up a UV environment for the MCP server. This creates an isolated Python environment while allowing the GNURadio Python package to be used.

cd gr-mcp
uv venv --system-site-packages

Add the MCP server configuration to your client configuration. Use the standard MCP JSON snippet to point your client at the local UV-based server.

Client configuration example

"mcpServers": {
  "gr_mcp": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/gr-mcp",
      "run",
      "main.py"
    ]
  }
}

Available tools

mcp_api

Provides a robust MCP API surface to interact with GNURadio flowgraphs programmatically.

flowgraph_builder

Programmatically construct, edit, and save .grc flowgraph files through code.

llm_integration

Designed for AI and automation integration to drive flowgraph generation and control.

extensible_architecture

Modular, extensible server architecture that supports custom modules and plugins.

unit_tests

Comprehensive tests to validate MCP server behavior using pytest.