UniFi MCP Server

Overview Schema Source Related Servers Discussions Admin

connector_protect_patch

Send PATCH requests to the UniFi Protect API through a cloud connector, using dry-run previews and confirmation before applying changes.

Instructions

Proxy a PATCH request to the Protect Application via Cloud Connector.

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": {
      "console_id": "<console_id>",
      "path": "<path>"
    },
    "name": "connector_protect_patch"
  }
}

Input Schema

Name	Required	Description
`body`	No	Optional request body
`path`	Yes	Protect API sub-path
`confirm`	No	Must be True to execute
`dry_run`	No	Preview without sending
`console_id`	Yes	UniFi console/host identifier
`controller`	No	Controller to run against (see list_controllers). Defaults to the controller chosen with select_controller, then the server default.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv0.6.4Oct 27, 2026

addedInput schema / properties / body / description
```
Added value: +"Optional request body"
```
addedInput schema / properties / confirm / description
```
Added value: +"Must be True to execute"
```
addedInput schema / properties / console_id / description
```
Added value: +"UniFi console/host identifier"
```
addedInput schema / properties / dry_run / description
```
Added value: +"Preview without sending"
```
addedInput schema / properties / path / description
```
Added value: +"Protect API sub-path"
```
removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / properties

Added value: +{
+  "result": {
+    "anyOf": [
+      {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      {
+        "items": {},
+        "type": "array"
+      }
+    ]
+  }
+}

addedOutput schema / required
```
Added value: +[
+  "result"
+]
```
addedOutput schema / x-fastmcp-wrap-result
```
Added value: +true
```

Changed1 schema field changedv0.6.0Oct 12, 2026

addedInput schema / properties / controller

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Controller to run against (see list_controllers). Defaults to the controller chosen with select_controller, then the server default."
+}

First observedv0.2.0Jun 27, 2026

TDQS

C2.4/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden. It implies a mutation and remote routing through a Cloud Connector, but says nothing about the confirm/dry_run safety gate, permission requirements, what happens on failure, or that PATCH semantics apply server-side. Only the barest mutation signal is present.

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?

A single front-loaded sentence with no padding or repetition. It is efficient, though efficiency here partly reflects how little it says.

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

Completeness2/5

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

For a mutation tool with no annotations, an output schema, and a confirm-gated execution model, the description is missing the behavioral context an agent needs: that confirm must be true, that dry_run previews, and how controller/console targeting works. Relying entirely on schema field descriptions leaves the operational semantics unexplained.

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 description coverage is 100%, so all six parameters are already documented in the schema. The description adds no meaning beyond that – it doesn't explain path formats, body shape, or the controller resolution order. Baseline 3 is appropriate when the schema does the heavy lifting.

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

Purpose3/5

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

It names a verb (proxy), an HTTP method (PATCH), and a target (Protect Application via Cloud Connector), which is more than the name alone. But 'proxy a PATCH request' largely restates 'connector_protect_patch', and nothing tells the agent what kind of Protect resources are patched or how this differs from connector_protect_put/post beyond the HTTP verb.

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

Usage Guidelines1/5

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

There is no guidance on when to choose PATCH over connector_protect_put, connector_protect_post, or connector_protect_get, nor any mention of prerequisites such as selecting a controller first. The agent must infer everything from the method name.

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

Deploy Server