Bagel

v1.0.0Developer Toolsstable

ChatGPT for physical data. Troubleshoot your robots and drones with natural language. No fuss.

ardupilotbetaflightdronemcppx4-autopilot
Share:
380
Stars
0
Downloads
0
Weekly
0/5

What is Bagel?

Bagel is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to chatgpt for physical data. troubleshoot your robots and drones with natural language. no fuss.

ChatGPT for physical data. Troubleshoot your robots and drones with natural language. No fuss.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • ChatGPT for physical data. Troubleshoot your robots and dron

Use Cases

Troubleshoot robots and drones with natural language.
Debug physical systems.
Interact with robotics platforms.
Extelligence-ai

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedApr 27, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx bagel

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Bagel

Bagel is a Docker-based MCP server that connects AI agents to physical robotics and drone data sources using natural language, eliminating the need for deep domain expertise to troubleshoot robots, drones, or flight controllers. It supports ROS2 (Kilted, Jazzy, Iron, Humble), ROS1 (Noetic), and flight-log formats from PX4, ArduPilot, and Betaflight by spinning up the appropriate pre-configured Docker container and exposing an SSE MCP endpoint. The agent can query metadata, generate DuckDB SQL queries against Apache Arrow data files, and run extensible POML-based analysis capabilities. This makes it a practical tool for robotics engineers and drone pilots who want to debug systems or analyze telemetry data conversationally.

Prerequisites

  • Docker Desktop installed and running
  • Git to clone the repository
  • An MCP-compatible AI client such as Claude Code that supports SSE transport
  • Physical or simulated robot/drone data files (ROS2 bags, PX4 logs, ArduPilot logs, Betaflight blackbox files)
1

Clone the Bagel repository

Clone the repository to your local machine. All configuration and Docker Compose files are included.

git clone https://github.com/Extelligence-ai/bagel.git && cd bagel
2

Start the appropriate Docker service

Choose the Docker service that matches your robotics platform. Available services include ros2-kilted, ros2-jazzy, ros2-iron, ros2-humble, ros1-noetic, px4, ardupilot, and betaflight.

docker compose run --service-ports ros2-kilted
3

Connect Claude Code via SSE transport

In a separate terminal, add Bagel as an MCP server to Claude Code using the SSE transport pointing at the running container's endpoint.

claude mcp add --transport sse bagel http://0.0.0.0:8000/sse
4

Mount your data files (optional)

To analyze your own robot or drone data files, edit compose.yaml and uncomment the volumes section, then map your local data directory into the container.

5

Start an AI session and begin querying

Launch Claude Code and start asking questions about your data in plain language. No SQL or ROS expertise required.

claude

Bagel Examples

Client configuration

SSE-based MCP client configuration for Bagel, pointing at the Docker container's SSE endpoint. Use this in clients that support SSE transport configuration.

{
  "mcpServers": {
    "bagel": {
      "url": "http://0.0.0.0:8000/sse",
      "transport": "sse"
    }
  }
}

Prompts to try

Example natural language queries for debugging robots and analyzing drone or ROS data.

- "Summarize the metadata of the ROS2 bag at ./data/sample/ros2/mcap"
- "What topics are published in this ROS2 bag and at what frequency?"
- "Run the POML capability './src/agent/examples/woof.poml' on my drone log"
- "Show me any error messages or anomalies in the PX4 flight log"
- "What was the maximum altitude reached in this ArduPilot log?"

Troubleshooting Bagel

Docker container starts but the SSE endpoint is not reachable

Ensure you used the --service-ports flag with docker compose run (not just docker compose up). Without this flag, ports are not published to the host. Verify with 'curl http://0.0.0.0:8000/sse'.

Agent cannot read my local data files

Edit compose.yaml and uncomment the volumes section to mount your local data directory into the container. For example, add '- /local/path/to/data:/app/data' under the volumes key for your service.

Wrong ROS version or flight controller format selected

Stop the current container and restart with the correct service name: ros2-kilted, ros2-jazzy, ros2-iron, ros2-humble, ros1-noetic, ros1-noetic-cv, px4, ardupilot, or betaflight.

Frequently Asked Questions about Bagel

What is Bagel?

Bagel is a Model Context Protocol (MCP) server that chatgpt for physical data. troubleshoot your robots and drones with natural language. no fuss. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Bagel?

Follow the installation instructions on the Bagel GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Bagel?

Bagel works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Bagel free to use?

Yes, Bagel is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "bagel": { "command": "npx", "args": ["-y", "bagel"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Bagel?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides