zscaler-mcp-server

Official

by zscaler

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

zia_list_devices

Read-only

List ZIA devices.

Instructions

List ZIA devices.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No
`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.
`user_ids`	No
`page_size`	No
`include_all`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv0.15.3Aug 19, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```
addedInput schema / properties / include_all / title
```
Added value: +"Include All"
```
addedInput schema / properties / name / title
```
Added value: +"Name"
```
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 / user_ids / title
```
Added value: +"User Ids"
```

addedInput schema / title

Added value: +"zia_list_devicesArguments"

Changed17 schema fields changedv0.14.0Jul 28, 2026

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

removedInput schema / properties / include_all / description

Removed value: -"Include or exclude Cloud Browser Isolation (CBI) devices. When True, CBI devices are included in the results. Default is True."

removedInput schema / properties / include_all / title
```
Removed value: -"Include All"
```

removedInput schema / properties / name / description

Removed value: -"Filter devices by name prefix (starts-with match). For example, 'Windows' matches 'Windows-PC-001', 'Windows-Laptop', etc."

removedInput schema / properties / name / title
```
Removed value: -"Name"
```

removedInput schema / properties / page / description

Removed value: -"Page number for pagination (1-based). Use with page_size to retrieve large device lists in chunks. Default starts at page 1."

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

removedInput schema / properties / page_size / description

Removed value: -"Number of devices per page. Default is 100, maximum is 1000. Use smaller values for faster responses, larger for fewer API calls."

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

changedInput schema / properties / user_ids / anyOf

Previous value: -[
-  {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

removedInput schema / properties / user_ids / description

Removed value: -"Filter devices by specific user IDs. Accepts a JSON array string or Python list of user ID strings. Example: '[\"12345\", \"67890\"]' or [\"12345\", \"67890\"]. Use zia_list_users to find user IDs."

removedInput schema / properties / user_ids / title
```
Removed value: -"User Ids"
```

removedInput schema / title

Removed value: -"zia_list_devicesArguments"

changedOutput schema / (root)

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

First observedv0.12.7Jun 24, 2026

TDQS

B3/5.0

Behavior3/5

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

Annotations include readOnlyHint=true and openWorldHint=false, indicating a read-only operation with complete listing semantics. The description adds no behavioral context beyond that. It does not describe pagination behavior, return format, or any side effects, but annotations already cover the safety profile. Since annotations are present, the description is minimally sufficient but adds little. No contradiction.

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

Conciseness3/5

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

The main description is overly terse at just 'List ZIA devices.' while the schema contains a lengthy and valuable description for the query parameter. The tool description itself is minimal but not wasteful. The query parameter's text is long but necessary and well-structured. Overall, description is acceptable but could be more informative without being verbose.

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?

For a list tool with read-only annotations and no output schema, the description is adequate for the basic purpose but lacks context on pagination, sorting, or filtering behavior. The query parameter does provide important operational guidance. However, the tool does not explain what 'ZIA devices' are in this context, or how results are ordered. With six parameters and zero required, there is room for more guidance on typical use cases.

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 only 17%, but the description provides no parameter details. However, the query parameter has a rich description that explains JMESPath semantics, field naming pitfalls, and suggests a safe initial call. This adds substantial meaning beyond the schema. Other parameters (name, page, user_ids, page_size, include_all) lack description, but the query description alone compensates for the low coverage. A score of 4 reflects the high-value explanatory content for the most complex parameter.

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?

The description 'List ZIA devices' states the verb and resource, and the name confirms the same. It is clear enough about what it does but does not distinguish from sibling tools like zia_list_devices_lite or zdx_list_devices. No additional context clarifies scope or differences.

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

Usage Guidelines2/5

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

No guidance provided on when to use this tool versus alternatives. The description simply states the action. For instance, there is no mention of when to use zia_list_devices vs zia_list_devices_lite, or whether the device context differs from zdx_list_devices. No exclusions or contextual cues are present.

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

Deploy Server

zia_list_devices

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools