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.
/plugin marketplace add dinglebear-ai/unraidnpx agentmods add plugins/dinglebear-ai/unraid/unraid-pygit clone --depth 1 https://github.com/dinglebear-ai/unraidGrade 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 3d 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": "2.10.1",
"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.
- 3d ago First seen · 50 lines scan A 57c47a56e33e
unraid-mcp is a plugin published in the GitHub repository dinglebear-ai/unraid (129 stars, last pushed 2d ago), 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
api-gateway-configuration
Configures API gateways for routing, authentication, rate limiting, and request transformation in microservice architectures. Use when setting up Kong, Nginx, AWS API Gateway, or Traefik for centralized API management.
kastell
Server security auditing, hardening, and fleet management. Runtime-derived audit catalog, CIS/PCI-DSS/HIPAA compliance, production hardening workflows, and first-party MCP tools. Supports Hetzner, DigitalOcean, Vultr, Linode with Coolify, Dokploy, and bare VPS modes.
kastell-plugin
Autonomous server security and infrastructure management. First-party MCP tools for cloud server provisioning, security auditing, hardening, backup, and fleet management across Hetzner, DigitalOcean, Vultr, and Linode.
swag-mcp
SWAG reverse proxy configuration management via MCP. Create, edit, view, and manage nginx proxy configurations with auth integration.
gpu-server-setup
Prepare a Linux server with NVIDIA GPUs for LLM and neural-network workloads: NVIDIA driver + CUDA from the official repo, Docker Engine + NVIDIA Container Toolkit as the mandatory base, GPU passthrough into containers, staged verification gates, optional docker-compose presets for vLLM, Infinity, OpenWebUI and Ollama.
easypanel-mcp-server marketplace
Full control of Easypanel from Claude Code, Cursor and Claude Desktop — deploy (app & compose), runtime logs, container exec, env vars, domains, databases, volumes, ports, resource limits, Docker maintenance and monitoring. 57 tools with built-in safety guards, optional read-only mode, plus an easypanelraw escape hatc.