BracketBot Multi-Robot Control

by bracketbotcapstone

Not rated

GitHub

About

Enables simultaneous control of multiple robots through a unified interface for movement, sound playback, camera access, and status monitoring with precise velocity control and comprehensive error handling.

Details

Author: bracketbotcapstone
Repository: BracketBotCapstone/bracketbot-mcp
Categories: AI, Design, Developer Tools, Media, Knowledge Base, API
Tags: #integration

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 BracketBot Multi-Robot Control

Command (node, npx, python, etc.) npx
Arguments
- Argument 1 -y
- Argument 2 @highlight/mcp-server
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

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "/c",
                "npx",
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "/c",
                "npx",
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "/c",
                "npx",
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "/c",
                "npx",
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "/c",
                "npx",
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "cmd"
        }
    }
}

JSON

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

From the repository

1. Start the robot control FastAPI servers:
- First robot on port 8000
- any other robots on 8001, 8002, etc

2. Important Update: The Claude desktop client now automatically runs the MCP server for you
- No need to manually start the server with python server.py
- The MCP server functionality is integrated directly into the Claude desktop client

3. The MCP server allows AI agents to control multiple robots and access their cameras.

`drive_forward`

Move a robot forward. Accepts a `port` parameter to specify which robot to control.

`drive_backward`

Move a robot backward. Accepts a `port` parameter to specify which robot to control.

`turn_left`

Turn a robot left. Accepts a `port` parameter to specify which robot to control.

`turn_right`

Turn a robot right. Accepts a `port` parameter to specify which robot to control.

`stop`

Stop robot movement. Accepts a `port` parameter to specify which robot to control.

`drive`

Control a robot with precise velocity values. Accepts a `port` parameter to specify which robot to control.

`beep`

Play a sound through a robot's speaker. Accepts a `port` parameter to specify which robot to control.

`get_camera_image`

Get an image from a robot's camera. Accepts a `port` parameter to specify which robot to control.

`robot_status`

Get robot status information. Accepts a `port` parameter to specify which robot to control.

`list_available_robots`

List all available robots and their status.

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

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "bracketbot multi-robot control": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Macos

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Windows

{
    "env": [],
    "args": [
        "/c",
        "npx",
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "cmd"
}

Multi-Robot Control MCP Agent

This project creates an MCP (Model Context Protocol) server that allows AI agents to control multiple robots via existing FastAPI robot control servers.

Features

Prerequisites

- Python 3.10+
- UV (Python package manager)
- Multiple running robot control FastAPI servers (as provided in the example)

Setup

1. Ensure you have a Python 3.10 environment active
2. Install dependencies using UV:

   uv pip install -e .

Usage

1. Start the robot control FastAPI servers:
- First robot on port 8000
- any other robots on 8001, 8002, etc

3. The MCP server allows AI agents to control multiple robots and access their cameras.

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

Available Resources

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

Examples

# 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()

Note on Image Handling

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

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

drive_forward

drive_backward

turn_left

turn_right

stop

drive

beep

get_camera_image

robot_status

list_available_robots

Claude Desktop / Cursor

Linux

Macos

Windows

Multi-Robot Control MCP Agent

Features

Prerequisites

Setup

Usage

Available Tools

Movement Control

Audio Control

Camera Access

System Information

Available Resources

Examples

Get status from robot on port 8001

Make both robots beep with different tones

Get a list of all available robots

Note on Image Handling

Install

More like this

Sentry

Github

Git

GitLab

Context 7

1Panel

`drive_forward`

`drive_backward`

`turn_left`

`turn_right`

`stop`

`drive`

`beep`

`get_camera_image`

`robot_status`

`list_available_robots`