bagel
v0.2.6Skills and MCP connection for Bagel: query rosbags, MCAP, CAN, MDF4, PX4/ArduPilot/Betaflight logs and live robot data in plain language; author event-windowed data-reduction pipelines; export to Rerun, Lichtblick, PlotJuggler, and LeRobot. Requires the Bagel server running locally (`uvx bagel-mcp`, or Docker for live robots); setup: https://github.com/Extelligence-ai/bagel
By ExtelligenceLicense: Apache-2.0397 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 5 skill or MCP entries
- Source updated
- Oct 4, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install bagel for Codex and Claude Code
codex plugin marketplace add Extelligence-ai/bagel
codex plugin marketplace upgrade bagel-dev
codex plugin add bagel@bagel-devPaste and run these commands in a terminal with Codex. They add and refresh the bagel-dev catalog, then install this plugin.
Compatibility: the page URL and API slug “bagel” remain stable.
- Codex:
bagel@agent-plugin-marketplace→bagel@bagel-dev
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/Extelligence-ai/bagelClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugin/.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json├── skills/authoring-pipelines/SKILL.md├── skills/exporting-visualizations/SKILL.md├── skills/operating-live-sinks/SKILL.md├── skills/triaging-robot-logs/SKILL.md└── .mcp.json
Included Skills4
Use when the user wants a bagel data pipeline — reducing a log to windows around events ("keep 30s around every hard brake"), recurring snippets/GIFs/exports, or any tasks-and-gates automation over robot data.
Use when the user wants to SEE robot data — visualize, plot, replay, or export a log or query result from bagel to a viewer or training format (Rerun, Lichtblick, PlotJuggler, LeRobot).
Use when subscribing to live robot data (MQTT, rosbridge) through bagel, managing standing pipelines that survive restarts, or when questions about live-buffer sizes and disk usage come up.
Use when investigating a robot log or flight log with bagel — finding events, anomalies, or "what happened around X" in rosbags, MCAP, CAN, MDF4, ULog, or Betaflight files. Read-only triage through the bagel MCP tools.
MCP servers1
- url
- http://localhost:8000/mcp
Plugin manifests2
{
"name": "bagel",
"version": "0.2.6",
"description": "Skills and MCP connection for Bagel: query rosbags, MCAP, CAN, MDF4, PX4/ArduPilot/Betaflight logs and live robot data in plain language; author event-windowed data-reduction pipelines; export to Rerun, Lichtblick, PlotJuggler, and LeRobot. Requires the Bagel server running locally (`uvx bagel-mcp`, or Docker for live robots); setup: https://github.com/Extelligence-ai/bagel",
"author": {
"name": "Extelligence",
"url": "https://github.com/Extelligence-ai/bagel"
},
"homepage": "https://github.com/Extelligence-ai/bagel",
"repository": "https://github.com/Extelligence-ai/bagel",
"license": "Apache-2.0",
"keywords": [
"robotics",
"ros",
"mcap",
"drones",
"iot",
"data-analysis",
"mcp"
],
"skills": "./skills/",
"mcpServers": "./.mcp.json",
"interface": {
"displayName": "Bagel",
"shortDescription": "Query robot data in English",
"longDescription": "Bagel lets you ask questions about robotics, drone, and IoT data (ROS 1/2 bags, MCAP, PX4/ArduPilot/Betaflight logs, CAN/MF4, live MQTT) in plain English. Every answer is computed by DuckDB SQL over the actual messages and the query is shown for audit. Bagel also has an intelligent edge data reduction pipeline: describe an event once, preview what would be kept, then run it on the robot. The plugin adds four skills that teach the agent the server's own workflows: triage, pipeline authoring, live sinks, and export to Rerun / Lichtblick / PlotJuggler / LeRobot. Bagel runs on your machine, so your data never leaves it: `uvx bagel-mcp` serves ROS 1/2 bags, flight logs, MCAP, CAN/MDF and CSV with no Docker, and the Docker images add live robots and fleet deployments; then connect Codex once with `codex mcp add bagel --url http://localhost:8000/mcp`.",
"developerName": "Extelligence",
"websiteURL": "https://trybagel.com/",
"privacyPolicyURL": "https://trybagel.com/privacy/",
"termsOfServiceURL": "https://trybagel.com/terms/",
"category": "Developer Tools",
"defaultPrompt": "Summarize the metadata of ./data/sample/ros2/mcap",
"capabilities": [
"log-triage",
"sql-over-messages",
"data-reduction-pipelines",
"visualization-export"
],
"logo": "./assets/logo.png",
"composerIcon": "./assets/composer-icon.png"
}
}{
"name": "bagel",
"description": "Skills and MCP connection for Bagel: query rosbags, MCAP, CAN, MDF4, PX4/ArduPilot/Betaflight logs and live robot data in plain language; author event-windowed data-reduction pipelines; export to Rerun, Lichtblick, PlotJuggler, and LeRobot. Requires the Bagel server running locally (`uvx bagel-mcp`, or Docker for live robots); setup: https://github.com/Extelligence-ai/bagel",
"version": "0.2.6",
"author": {
"name": "Extelligence",
"url": "https://github.com/Extelligence-ai/bagel"
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[bagel on Agent Plugins Marketplace](https://pluginsmp.com/plugins/bagel)