Tello Drone MCP Server
A MCP server for controlling a drone
0xKoda
README
Tello Drone MCP Server
A Model Context Protocol (MCP) server implementation for controlling the DJI Tello drone. This server allows any MCP-compatible client to control a Tello drone through a standardized interface.
This is under active development, read security considerations
Features
- MCP Support
- Real-time drone control through SSE (Server-Sent Events)
- Robust error handling and logging
- CORS-enabled for web clients (like mcp inspector)
- Supports basic Tello drone commands:
- Takeoff
- Land
- Move (up/down/left/right/forward/back)
- Rotate (clockwise/counter-clockwise)
Prerequisites
- Python 3.7+
- DJI Tello drone
- Network connection to the Tello drone
- Root/sudo access (required for UDP socket binding)
Installation
- Clone this repository:
git clone <repository-url>
cd drone-mcp
- Install dependencies:
pip install -r requirements.txt
MCP Configuration
To enable your MCP client to connect to the Tello drone server, add the following configuration to your mcp.json
file (usually located at ~/.cursor/mcp.json
or in your project directory):
{
"tello-drone": {
"url": "http://localhost:3000/sse"
}
}
This configuration allows MCP-enabled tools and models to automatically discover and connect to your Tello drone server.
Usage
-
Connect to your Tello drone's WiFi network (usually starts with "TELLO-").
-
Start the MCP server:
sudo python tello_mcp.py
The server will:
- Initialize connection with the Tello drone
- Start the MCP server on
http://0.0.0.0:3000
- Set up SSE endpoint at
/sse
- Handle messages at
/message
Ensure the server is running before you plan to use it in your client (cursor, windsurf, code).
Available Tools
The server provides the following MCP tools:
1. Takeoff
{
"name": "takeoff",
"description": "Commands the Tello drone to take off",
"inputSchema": {
"type": "object",
"properties": {}
}
}
2. Land
{
"name": "land",
"description": "Commands the Tello drone to land",
"inputSchema": {
"type": "object",
"properties": {}
}
}
3. Move
{
"name": "move",
"description": "Moves the Tello drone in a specified direction",
"inputSchema": {
"type": "object",
"properties": {
"direction": {
"type": "string",
"enum": ["up", "down", "left", "right", "forward", "back"]
},
"distance": {
"type": "integer",
"minimum": 20,
"maximum": 500
}
},
"required": ["direction", "distance"]
}
}
4. Rotate
{
"name": "rotate",
"description": "Rotates the Tello drone clockwise or counter-clockwise",
"inputSchema": {
"type": "object",
"properties": {
"direction": {
"type": "string",
"enum": ["cw", "ccw"]
},
"degrees": {
"type": "integer",
"minimum": 1,
"maximum": 3600
}
},
"required": ["direction", "degrees"]
}
}
MCP Client Integration
To connect an MCP client:
- Start your server and Connect to the SSE endpoint:
GET http://localhost:3000/sse
- Prompt your MCP enabled model, which will communicate via SSE
event: endpoint
data: /message?sessionId=<session-id>
- Send initialize request:
{
"jsonrpc": "2.0",
"id": 1,
"method": "initialize"
}
- List available tools:
{
"jsonrpc": "2.0",
"id": 2,
"method": "listTools"
}
- Call a tool (example - takeoff):
{
"jsonrpc": "2.0",
"id": 3,
"method": "callTool",
"params": {
"name": "takeoff",
"arguments": {}
}
}
Error Handling
The server implements comprehensive error handling:
- Drone connection failures
- Invalid commands
- Network timeouts
- Protocol errors
- Invalid tool parameters
All errors are logged and returned as proper JSON-RPC 2.0 error responses.
Logging
The server logs to stderr with detailed information about:
- Server startup/shutdown
- Drone connection status
- Command execution
- Client connections
- Error conditions
Security Considerations
- The server requires root/sudo access to bind to UDP ports
- No authentication is implemented (rely on network security)
- CORS is enabled for all origins (*)
- Use in a controlled environment only
Development
The server is built using:
- Python's
mcp
library for protocol handling - Starlette for HTTP/SSE transport
- Uvicorn as the ASGI server
- Native Python socket library for drone UDP communication
Troubleshooting
-
Server won't start:
- Ensure you have sudo/root access
- Check if the Tello's WiFi is connected
- Verify no other process is using port 3000
-
Drone won't connect:
- Ensure drone is powered on
- Check WiFi connection
- Verify no other application is controlling the drone
-
Commands fail:
- Check drone battery level
- Ensure drone is in a safe flying environment
- Verify command parameters are within allowed ranges
License
MIT
Contributing
Welcome to contribute.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.