Extelligence-ai/bagel

Query robotics, drone, and IoT data in plain English through an MCP server, with an intelligent edge data reduction pipeline that keeps only the data that matters.

What it solves

Bagel provides a natural-language interface for analyzing robotics, drone, and IoT data. It eliminates the need for writing custom parsing scripts, manually scrubbing through timelines in tools like PlotJuggler, or using complex CLI commands to extract insights from large log files across various formats.

How it works

Bagel acts as an MCP (Model Context Protocol) server that connects LLMs (like Claude, Gemini, or local models) to robotics data. When a user asks a question in plain English, Bagel translates that request into deterministic DuckDB SQL queries to perform calculations on the data, ensuring the LLM does not perform the math itself. It also features an edge data reduction pipeline that can run on the robot to detect specific events described in natural language and save only the relevant time windows, reducing the amount of data that needs to be transferred.

Who it’s for

Robotics engineers, drone pilots, and IoT developers who need to analyze telemetry, logs, and sensor data across multiple formats (ROS1/2, PX4, ArduPilot, MQTT, etc.) without needing deep domain expertise in every specific log format.

Highlights

  • Deterministic Analysis: Uses SQL for calculations to avoid LLM "hallucinations" in math.
  • Broad Format Support: Compatible with ROS1, ROS2, MCAP, PX4, ArduPilot, Betaflight, CAN/MDF4, and MQTT.
  • Intelligent Edge Reduction: Reduces data volume by keeping only event-specific windows based on natural language descriptions.
  • LLM Integration: Works as an MCP server for Claude Code, Cursor, Gemini, and local models via Ollama.
  • Transparent Auditing: Shows the generated SQL queries so users can verify the calculations.

Related

  • Project
    svnscha/mcp-windbg

    A Model Context Protocol server that enables AI models to perform automated Windows crash dump analysis and live debugging by wrapping the standard WinDbg command-line tools.

  • Project
    microsoft/powerbi-modeling-mcp

    An MCP server that enables AI agents to build and modify Power BI semantic models using natural language, supporting bulk operations and DAX validation.

  • Project
    dbt-labs/dbt-mcp

    dbt‑MCP Server is an open‑source service that exposes a large catalog of dbt‑related tools (SQL execution, semantic‑layer queries, model discovery, dbt CLI commands, job administration, code generation, and documentation lookup) via the Model Context Protocol. It lets LLM‑powered agents understand and act on a dbt project—generating SQL from natural language, running dbt jobs, fetching lineage, and even creating new model files—making it a concrete bridge between data‑engineering metadata and AI assistants.

  • Project
    dataease/SQLBot

    An intelligent data querying system based on LLMs and RAG that enables conversational data analysis (ChatBI) by converting natural language into SQL and visual charts.

  • Project
    apconw/Aix-DB

    Aix-DB is an open‑source platform that converts natural‑language questions into SQL queries and visual dashboards, enabling conversational data analysis across many databases.