zscaler-mcp-server

Official

by zscaler

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

zcc_list_devices

Read-only

List ZCC enrolled devices (read-only).

Instructions

List ZCC enrolled devices (read-only).

Each row is the full device record — identity, OS, agent version, registration state, assigned policy_name, ownership, hardware, VPN/tunnel state, and the enrollment / keep-alive timestamps. Use the returned udid with zcc_get_device_otp.

Input Schema

TableJSON Schema

Name	Required	Description
`page`	No
`query`	No	Optional JMESPath expression applied to the results after the API call, for client-side filtering and projection. Examples: "[?enabled==`true`]", "[*].{name: name, id: id}", "length(@)". Omit to get the full records. IMPORTANT: field names are the keys of the returned records, which are usually snake_case (`custom_category`) even where the Zscaler API documents camelCase (`customCategory`) — guessing the spelling yields an empty list that looks like a real answer. If you have not already seen a record from this tool, call it once without `query` and read the keys off the response.
`os_type`	No
`username`	No
`page_size`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv0.15.3Aug 19, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```
addedInput schema / properties / os_type / title
```
Added value: +"Os Type"
```
addedInput schema / properties / page / title
```
Added value: +"Page"
```
addedInput schema / properties / page_size / title
```
Added value: +"Page Size"
```

changedInput schema / properties / query / description

Previous value: -"Optional JMESPath expression applied to the results after the API call, for client-side filtering and projection. Field names are exactly what the Zscaler API returns. Examples: \"[?enabled==`true`]\", \"[*].{name: name, id: id}\", \"length(@)\". Omit to get the full records."New value: +"Optional JMESPath expression applied to the results after the API call, for client-side filtering and projection. Examples: \"[?enabled==`true`]\", \"[*].{name: name, id: id}\", \"length(@)\". Omit to get the full records. IMPORTANT: field names are the keys of the returned records, which are usually snake_case (`custom_category`) even where the Zscaler API documents camelCase (`customCategory`) — guessing the spelling yields an empty list that looks like a real answer. If you have not already seen a record from this tool, call it once without `query` and read the keys off the response."

addedInput schema / properties / query / title
```
Added value: +"Query"
```
addedInput schema / properties / username / title
```
Added value: +"Username"
```

addedInput schema / title

Added value: +"zcc_list_devicesArguments"

Changed14 schema fields changedv0.14.0Jul 28, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

removedInput schema / properties / os_type / description

Removed value: -"Device operating system type: ios, android, windows, macos, linux."

removedInput schema / properties / os_type / title
```
Removed value: -"Os Type"
```

removedInput schema / properties / page / description

Removed value: -"Page number for paginated results."

removedInput schema / properties / page / title
```
Removed value: -"Page"
```

removedInput schema / properties / page_size / description

Removed value: -"Number of results per page. Default is 50. Max is 5000."

removedInput schema / properties / page_size / title
```
Removed value: -"Page Size"
```

changedInput schema / properties / query / description

Previous value: -"JMESPath expression for client-side filtering/projection of results."New value: +"Optional JMESPath expression applied to the results after the API call, for client-side filtering and projection. Field names are exactly what the Zscaler API returns. Examples: \"[?enabled==`true`]\", \"[*].{name: name, id: id}\", \"length(@)\". Omit to get the full records."

removedInput schema / properties / query / title
```
Removed value: -"Query"
```

removedInput schema / properties / service

Removed value: -{
-  "default": "zcc",
-  "description": "The service to use.",
-  "title": "Service",
-  "type": "string"
-}

removedInput schema / properties / username / description

Removed value: -"Username to filter by (e.g., 'jdoe@acme.com')."

removedInput schema / properties / username / title
```
Removed value: -"Username"
```

removedInput schema / title

Removed value: -"zcc_list_devicesArguments"

changedOutput schema / (root)

Previous value: -{
-  "properties": {
-    "result": {
-      "items": {
-        "additionalProperties": true,
-        "type": "object"
-      },
-      "title": "Result",
-      "type": "array"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "title": "zcc_list_devicesOutput",
-  "type": "object"
-}New value: +null

First observedv0.12.7Jun 24, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, so the read-only nature is known. The description adds value by enumerating the fields included per row (identity, OS, agent version, etc.) and the udid relationship, which helps the agent understand the response shape.

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 two sentences long, with the purpose stated first, followed by row content details. Every sentence adds information without redundancy.

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

Completeness3/5

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

The description covers the response contents well but omits pagination details, filter semantics, and any note about the query parameter. Given the tool's 5 optional parameters and missing output schema, there are notable gaps, though the read-only annotation and field list provide a solid baseline.

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

Parameters2/5

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

Schema description coverage is only 20%, with only the query parameter documented. The tool description provides no additional explanation for page, page_size, os_type, or username, leaving the agent to infer their meanings from parameter names alone.

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 uses a specific verb 'List' with a clear resource 'ZCC enrolled devices', and explicitly marks it read-only. This distinguishes it from sibling tools like zdx_list_devices and zia_list_devices.

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?

The description gives clear context about what records are returned and points to a specific downstream use (zcc_get_device_otp). However, it does not explicitly mention alternative tools or exclusions, though the ZCC prefix and content differentiate it.

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

Deploy Server

zcc_list_devices

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools