BracketBot Multi-Robot Control MCP server

This MCP server enables AI agents to control multiple robots simultaneously through existing FastAPI robot control servers. It provides a unified interface for movement, audio, camera access, and status monitoring across multiple robots.

Prerequisites

• Python 3.10+
• UV (Python package manager)
• Multiple running robot control FastAPI servers

Installation

Ensure you have a Python 3.10 environment active, then install dependencies using UV:

uv pip install -e .

Running the Service

Important: The Claude desktop client now automatically runs the MCP server for you. There's no need to manually start the server with python server.py as the functionality is integrated directly into the Claude desktop client.

Using the MCP Server

Before using the MCP server, ensure your robot control FastAPI servers are running:

• First robot on port 8000
• Additional robots on ports 8001, 8002, etc.

Available Tools

All tools accept a port parameter (default: 8000) to specify which robot to control.

Movement Control

• drive_forward: Move a robot forward
• drive_backward: Move a robot backward
• turn_left: Turn a robot left
• turn_right: Turn a robot right
• stop: Stop robot movement
• drive: Control with precise velocity values

Audio Control

• beep: Play a sound through a robot's speaker

Camera Access

• get_camera_image: Get an image from a robot's camera

System Information

• robot_status: Get robot status information
• list_available_robots: List all available robots and their status

Resources

• robot://info/{port}: Get information about a specific robot's capabilities

Usage Examples

Here are some examples of how to control multiple robots:

# Get status from robot on port 8000
status_robot1 = await client.robot_status(port=8000)

# Get status from robot on port 8001
status_robot2 = await client.robot_status(port=8001)

# Make both robots beep with different tones
await client.beep(port=8000, frequency=440, duration=1.0)  # A4 note on robot 1
await client.beep(port=8001, frequency=523.25, duration=1.0)  # C5 note on robot 2

# Get a list of all available robots
robots = await client.list_available_robots()

Image Handling

The camera image tools use MCP's native Image class for handling image data. This allows the AI agent to receive image data in a format that can be properly handled by the client without additional conversion.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "multi-robot-control" '{"command":"python","args":["-m","multi_robot_control.server"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "multi-robot-control": {
            "command": "python",
            "args": [
                "-m",
                "multi_robot_control.server"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "multi-robot-control": {
            "command": "python",
            "args": [
                "-m",
                "multi_robot_control.server"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect