MAVLink MCP Server
About
MCP server for LLM to drone communication via MAVLink
Details
- Author
- ion-g-ion
- GitHub stars
- 21
- Downloads
- 291
- Categories
- Other
Jump to
- MCP server for MAVLink‑enabled drone systems
- Supports PX4 drone software
- Python 3.10+ required
- Installable via pip from requirements
- Runnable with standard Python or uv run
- Example agent using fastagent library included
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MAVLink MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
1. Clone the repository and install dependencies with pip install -r requirements.txt.
2. Run the server with python src/server/mavlinkmcp.py or uv run src/server/mavlinkmcp.py.
3. An example client is provided in example_agent.py using the fastagent library, which demonstrates creating an AI agent with human input for drone control.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mavlink mcp server": {
"MAVLinkMCP": {
"command": "python",
"args": [
"src/server/mavlinkmcp.py"
]
}
}
}
}McpServers
{
"MAVLinkMCP": {
"command": "python",
"args": [
"src/server/mavlinkmcp.py"
]
}
}MAVLink MCP Server
This repository contains a Python-based Model Context Protocol (MCP) server for interacting with MAVLink-enabled devices, such as drones running PX4 software.
Prerequisites
- Python 3.10 or higher
Installation
1. Clone the repository:
git clone https://github.com/yourusername/MAVLinkMCP.git
cd MAVLinkMCP
2. Install dependencies:
pip install -r requirements.txt
Usage
Run the MCP server with the following command:
python src/server/mavlinkmcp.py
Alternatively, you can run the server using uv run:
uv run src/server/mavlinkmcp.py
Example agent usage
An example client is implemented in example_agent.py using the fastagent library. This demonstrates how to create an AI agent that interacts with the MCP server and supports human input for controlling a drone.
Export the OpenAI key before running it.
Contributing
Contributions are welcome! Please fork the repository and submit a pull request.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
