ugreen-nas-mcp

Overview Schema Source Related Servers Discussions Admin

Pre-deployment checks

nas_docker_check

Read-only

Verify whether a host port, NAS folder, or GPU vendor is already used by Docker containers before deploying to prevent conflicts; results cover Docker only, not other NAS services.

Instructions

Check for conflicts before deploying. kind "port" tells whether a host port is taken by a container (needs port; protocol optional). kind "dir" tells whether a folder is mounted by a container (needs dir). kind "gpu" tells whether an app is using the discrete GPU of the given vendor (needs vendor; ask the user if unknown). These checks only see Docker containers: occupied: false does not guarantee that the port is free, because other services on the NAS are not covered.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "kind": "<kind>"
    },
    "name": "nas_docker_check"
  }
}

Input Schema

Name	Required	Description
`dir`	No	For "dir": absolute NAS folder.
`kind`	Yes	What to check.
`port`	No	For "port": the host port.
`vendor`	No	For "gpu": GPU vendor.
`protocol`	No	For "port": protocol; omit for the NAS default.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 13, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds a genuinely useful behavioral caveat that the check only inspects Docker containers and that occupied: false does not prove the port is free, which the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then a compact per-kind breakdown, then the scope caveat. The per-kind sentences are slightly clipped but every sentence carries information; nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, yet the description reveals the key result field (occupied) and its interpretation limits, which covers the main ambiguity for a read-only check tool. Remaining gaps are minor, such as not describing the gpu/dir result shape.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds conditional semantics the schema cannot express: which parameter is required per kind, that protocol may be omitted to use the NAS default, and that vendor should be resolved with the user.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: pre-deployment conflict checks, then enumerates the three concrete check kinds (port, dir, gpu). This clearly separates it from the container/image/log listing siblings, which do not perform occupancy checks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives per-kind conditions of use, including which parameter each kind requires and the explicit instruction to ask the user when the GPU vendor is unknown. It stops short of naming alternatives or stating when not to run the check at all.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.