Bagel

Overview

Bagel is a Model Context Protocol (MCP) server: Plain-English analysis of robotics, drone, and IoT data, with intelligent edge data reduction. In practice that means any MCP-compatible AI assistant can call Bagel's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Docker image ghcr.io/extelligence-ai/bagel/ros2-kilted:2.2.3 speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v2.2.3, published under the Apache-2.0 license, with source at Extelligence-ai/bagel on GitHub, where it has earned 396 stars.

Bagel is listed under Development on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Bagel for Extelligence-ai, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "bagel": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/extelligence-ai/bagel/ros2-kilted:2.2.3"
      ]
    }
  }
}