Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/kornia/bubbaloopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/kornia/bubbaloop/bubbaloop-mcp)<a href="https://agentmods.dev/plugins/kornia/bubbaloop/bubbaloop-mcp"><img src="https://agentmods.dev/badge/plugins/kornia/bubbaloop/bubbaloop-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/kornia/bubbaloop/bubbaloop-mcp"><img src="https://agentmods.dev/badge/plugins/kornia/bubbaloop/bubbaloop-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
bubbaloop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "bubbaloop",
"version": "0.1.0",
"description": "Control Bubbaloop — a multi-agent skill runtime for physical sensor nodes — directly from any MCP client. Wraps the bubbaloop daemon's MCP server (47 tools across Viewer/Operator/Admin RBAC tiers) with curated slash commands and a subagent for node lifecycle, mission management, and Zenoh stream introspection.",
"author": {
"name": "Edgar Riba",
"email": "[email protected]",
"url": "https://github.com/kornia/bubbaloop"
},
"homepage": "https://github.com/kornia/bubbaloop",
"repository": "https://github.com/kornia/bubbaloop",
"license": "Apache-2.0",
"keywords": [
"robotics",
"iot",
"zenoh",
"mcp",
"sensors",
"rtsp",
"agent",
"edge"
]
}
What it installs
The manifest is a name and a version. 1 skill, 8 commands, 3 agents travel with it, and installing the plugin installs all of them — 450 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill using-bubbaloop B 53 tokens
- Command doctor A 38 tokens
- Command node-validate A 18 tokens
- Command stream A 14 tokens
- Command node-new A 30 tokens
- Command diagnose A 13 tokens
- Command mission A 8 tokens
- Command nodes A 11 tokens
- Command status A 10 tokens
- Agent bubbaloop-core-contributor A 102 tokens
- Agent bubbaloop-node-author A 86 tokens
- Agent bubbaloop-operator A 67 tokens
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 24 lines scan A 6d5717069090
bubbaloop is a plugin published in the GitHub repository kornia/bubbaloop (29 stars, last pushed 3mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
text-to-cad
The text-to-cad plugin gives your agent local workflows for generating 3D models as STEP, GLB, STL or 3MF files. It also does design for manufacturing checks, generates engineering drawings, and connects to popular 3D printing, sheet metal and CNC fabrication services.
text-to-cad
The text-to-cad plugin gives your agent local workflows for generating 3D models as STEP, GLB, STL or 3MF files. It also does design for manufacturing checks, generates engineering drawings, and connects to popular 3D printing, sheet metal and CNC fabrication services.
bagel
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.
bagel
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.
ros2-engineering
Production-grade ROS 2 engineering guidance and validation tools.
gap marketplace
Plugin marketplace listing 2 plugins: gap, open-robot-skills.