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/dinglebear-ai/unraidWrote 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/dinglebear-ai/unraid/unraid-py)<a href="https://agentmods.dev/plugins/dinglebear-ai/unraid/unraid-py"><img src="https://agentmods.dev/badge/plugins/dinglebear-ai/unraid/unraid-py/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/dinglebear-ai/unraid/unraid-py"><img src="https://agentmods.dev/badge/plugins/dinglebear-ai/unraid/unraid-py.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
unraid-mcp 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 19d 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": "unraid-mcp",
"displayName": "Unraid MCP",
"version": "2.10.2",
"description": "Query, monitor, and manage Unraid servers via GraphQL API through MCP tools. Supports system info, Docker, VMs, array/parity, notifications, plugins, rclone, and live telemetry.",
"author": {
"name": "Jacob Magar",
"email": "[email protected]"
},
"repository": "https://github.com/dinglebear-ai/unraid",
"homepage": "https://github.com/dinglebear-ai/unraid",
"license": "MIT",
"keywords": [
"unraid",
"homelab",
"mcp",
"graphql",
"docker",
"nas",
"monitoring"
],
"mcpServers": "./.mcp.json",
"userConfig": {
"unraid_api_url": {
"type": "string",
"title": "Unraid GraphQL API URL",
"description": "Your Unraid server's GraphQL endpoint, e.g. https://tower.local/graphql. No trailing slash.",
"sensitive": true
},
"unraid_api_key": {
"type": "string",
"title": "Unraid API Key",
"description": "API key for your Unraid server. Found in Settings → Management Access → API Keys.",
"sensitive": true
},
"unraid_verify_ssl": {
"type": "string",
"title": "Verify TLS certificate",
"description": "Controls TLS verification of the Unraid API. Leave blank to verify (the default). Set to false to disable verification for a stock self-signed cert (you must also enable \"Allow insecure TLS\" below), or set to a path to a CA-bundle file to trust a self-signed cert without disabling verification.",
"default": ""
},
"unraid_allow_insecure_tls": {
"type": "boolean",
"title": "Allow insecure TLS",
"description": "Required second opt-in when \"Verify TLS certificate\" is set to false. Disabling verification sends your API key to an unverified peer over both HTTP and WebSocket connections, exposing it to man-in-the-middle interception. Only enable this on a trusted LAN.",
"default": false
}
}
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 109 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 19d ago Changed 809fe1418e64
- 1mo ago First seen · 50 lines scan A 57c47a56e33e
unraid-mcp is a plugin published in the GitHub repository dinglebear-ai/unraid (140 stars, last pushed yesterday), licensed MIT. 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
swag-mcp
SWAG reverse proxy configuration management via MCP. Create, edit, view, and manage nginx proxy configurations with auth integration.
swag-mcp
SWAG reverse proxy configuration management via MCP tools. Create, edit, view, and manage nginx proxy configurations with auth integration.
my-servicenow-skills
My skills for mcp-server-servicenow.
axon
Axon research, ingestion, retrieval, and operator skills for an existing service.
cortex
Cortex observability and investigation skills for an existing service.
umt
28 production-ready MCP servers for coding agents — filesystem, GitHub, npm, research, and more. Ships zero-config servers out of the box and the umt CLI to connect any harness.