zscaler-mcp-server

Official

by zscaler

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

zdx_list_devices

Read-only

List active ZDX devices.

Instructions

List active ZDX devices.

Read-only. Returns one identifying row per device (id, hostname, owning user). Filter by email, user ID, MAC/IP, location/department/geo, and the since HOURS window. Use a returned device id with zdx_get_device or the deep-trace / probe tools.

Input Schema

TableJSON Schema

Name	Required	Description
`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.
`since`	No
`emails`	No
`geo_id`	No
`offset`	No
`user_ids`	No
`location_id`	No
`mac_address`	No
`private_ipv4`	No
`department_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed13 schema fields changedv0.15.3Aug 19, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```
addedInput schema / properties / department_id / title
```
Added value: +"Department Id"
```
addedInput schema / properties / emails / title
```
Added value: +"Emails"
```
addedInput schema / properties / geo_id / title
```
Added value: +"Geo Id"
```
addedInput schema / properties / location_id / title
```
Added value: +"Location Id"
```
addedInput schema / properties / mac_address / title
```
Added value: +"Mac Address"
```
addedInput schema / properties / offset / title
```
Added value: +"Offset"
```
addedInput schema / properties / private_ipv4 / title
```
Added value: +"Private Ipv4"
```

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 / since / title
```
Added value: +"Since"
```
addedInput schema / properties / user_ids / title
```
Added value: +"User Ids"
```

addedInput schema / title

Added value: +"zdx_list_devicesArguments"

Changed24 schema fields changedv0.14.0Jul 28, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
removedInput schema / properties / department_id / description
```
Removed value: -"Filter by department ID(s)."
```
removedInput schema / properties / department_id / title
```
Removed value: -"Department Id"
```
removedInput schema / properties / emails / description
```
Removed value: -"Filter by email addresses."
```
removedInput schema / properties / emails / title
```
Removed value: -"Emails"
```
removedInput schema / properties / geo_id / description
```
Removed value: -"Filter by geolocation ID(s)."
```
removedInput schema / properties / geo_id / title
```
Removed value: -"Geo Id"
```
removedInput schema / properties / location_id / description
```
Removed value: -"Filter by location ID(s)."
```
removedInput schema / properties / location_id / title
```
Removed value: -"Location Id"
```
removedInput schema / properties / mac_address / description
```
Removed value: -"Filter by MAC address."
```
removedInput schema / properties / mac_address / title
```
Removed value: -"Mac Address"
```

removedInput schema / properties / offset / description

Removed value: -"Offset string for pagination (next_offset)."

removedInput schema / properties / offset / title
```
Removed value: -"Offset"
```
removedInput schema / properties / private_ipv4 / description
```
Removed value: -"Filter by private IPv4 address."
```
removedInput schema / properties / private_ipv4 / title
```
Removed value: -"Private Ipv4"
```

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": "zdx",
-  "description": "The service to use.",
-  "title": "Service",
-  "type": "string"
-}

removedInput schema / properties / since / description

Removed value: -"Number of hours to look back (default 2h)."

removedInput schema / properties / since / title
```
Removed value: -"Since"
```
removedInput schema / properties / user_ids / description
```
Removed value: -"Filter by user IDs."
```
removedInput schema / properties / user_ids / title
```
Removed value: -"User Ids"
```

removedInput schema / title

Removed value: -"zdx_list_devicesArguments"

changedOutput schema / (root)

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

First observedv0.12.7Jun 24, 2026

TDQS

A4.4/5.0

Behavior4/5

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

The description explicitly states 'Read-only', consistent with annotations' readOnlyHint=true, and adds useful behavioral details: return row contents, filtering capabilities, and the since HOURS window. It does not mention pagination or rate limits, but the provided context goes beyond the minimal annotation support.

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 compact — a single paragraph with three sentences — and each sentence earns its place: purpose, return structure, filters, and downstream usage. It is front-loaded with the main verb and resource and contains no filler.

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?

Given 10 parameters, no output schema, and minimal annotation, the description adequately covers the core elements: what is listed, what is returned, filter options, and how to use the results. It omits pagination/offset details and does not mention any ordering or default limits, but these are secondary for a listing tool with rich annotation support.

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?

With only 10% schema description coverage, the description compensates by enumerating the main filter parameters (email, user IDs, MAC/IP, location/department/geo, since). It adds meaning such as interpreting `since` as an 'HOURS window.' However, it does not describe offset or give format details for the filters, so it is informative but not exhaustive.

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 opens with 'List active ZDX devices', a specific verb and resource that clearly identifies the tool's function. It further defines the output as 'one identifying row per device (id, hostname, owning user)', which distinguishes it from device-related siblings like zdx_get_device and zdx_list_departments.

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 specifies usage context by explaining filter options (email, user ID, MAC/IP, location/department/geo, since) and explicitly instructs to 'Use a returned device id with zdx_get_device or the deep-trace / probe tools.' It does not provide an explicit 'when not to use' or name an alternative listing tool, so it falls short of a 5.

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

Deploy Server

zdx_list_devices

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools