UniFi Protect MCP

Overview Schema Source Related Servers Discussions Admin

protect_get_relay

Read-only

Retrieve complete configuration and status for a UniFi Protect relay by its ID, including LED settings, outputs, inputs, and connection state.

Instructions

Get full details for a specific relay by ID. Returns: id, modelKey, name, mac, state, type, guid, ledSettings (isEnabled), outputs (array), inputs (array), wirelessConnectionState (7.3.47 docs).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes	Relay ID

Output Schema

TableJSON Schema

Name	Required	Description
`id`	No	Device ID
`mac`	No	MAC address
`guid`	No	Hardware MODEL GUID, shared by every unit of the same model. NOT a per-device identifier — use `id` to identify a device.
`name`	No	Device name
`type`	No	Hardware model name, e.g. "UVC G6 Turret", "UP Chime PoE", "UNVR-PRO"
`state`	No	CONNECTED \| DISCONNECTED \| ...
`inputs`	No	Input channels (array of objects)
`outputs`	No	Output channels (array of objects)
`modelKey`	No	Resource kind
`ledSettings`	No	LED settings (object: isEnabled)
`wirelessConnectionState`	No	Wireless link state (object)

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv2.13.0Sep 20, 2026

addedOutput schema / properties / guid

Added value: +{
+  "description": "Hardware MODEL GUID, shared by every unit of the same model. NOT a per-device identifier — use `id` to identify a device.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / type

Added value: +{
+  "description": "Hardware model name, e.g. \"UVC G6 Turret\", \"UP Chime PoE\", \"UNVR-PRO\"",
+  "type": [
+    "string",
+    "null"
+  ]
+}

Changed8 schema fields changedv2.11.5Sep 13, 2026

removedOutput schema / properties / mac / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / mac / type

Added value: +[
+  "string",
+  "null"
+]

removedOutput schema / properties / modelKey / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / modelKey / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / name / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / name / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / state / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / state / type
```
Added value: +[
+  "string",
+  "null"
+]
```

Changed4 schema fields changedv2.7.5Jun 21, 2026

addedOutput schema / properties / inputs

Added value: +{
+  "description": "Input channels (array of objects)"
+}

addedOutput schema / properties / ledSettings

Added value: +{
+  "description": "LED settings (object: isEnabled)"
+}

addedOutput schema / properties / outputs

Added value: +{
+  "description": "Output channels (array of objects)"
+}

addedOutput schema / properties / wirelessConnectionState

Added value: +{
+  "description": "Wireless link state (object)"
+}

First observedv2.7.4Jun 11, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is covered. The description adds value by listing the returned fields and noting a version-specific field (wirelessConnectionState). No contradiction with annotations.

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

Conciseness5/5

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

The description is a single, front-loaded sentence that states the purpose and then lists returned fields. No wasted words, and the most important information (the verb and resource) appears first.

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

Completeness5/5

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

For a simple read-only tool with one parameter and no side effects, the description fully covers what it does, what it returns, and even a version note. An agent has everything needed to invoke it correctly, especially given the output schema exists.

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

Parameters3/5

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

Schema coverage is 100% (the id parameter is documented as 'Relay ID'). The description reinforces that the ID identifies a relay but does not add syntax or format details beyond the schema. The baseline of 3 applies because the schema carries the parameter semantics.

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?

The description states a specific verb ('Get') and resource ('full details for a specific relay by ID'), and it enumerates the returned fields. This clearly distinguishes it from sibling tools like protect_list_relays (which lists all relays) and other get_* tools. The purpose is unambiguous.

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

Usage Guidelines3/5

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

The description implies usage (when you need details for one relay by ID) but does not explicitly mention alternatives or exclusions. Given the sibling list_relays exists, an agent can infer the distinction, but there is no explicit guidance like 'use list_relays to enumerate all relays'.

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