zscaler-mcp-server

Official

by zscaler

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

zdx_get_application_metric

Read-only

Get ZDX performance metrics for one application (time-series).

Instructions

Get ZDX performance metrics for one application (time-series).

Read-only. Returns one series per metric (Page Fetch Time, DNS Time, availability), each with its datapoints over the since HOURS window (default 2h). Pass metric_name to narrow to a single metric. Use app_id from zdx_list_applications.

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
`app_id`	Yes
`geo_id`	No
`location_id`	No
`metric_name`	No
`department_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed10 schema fields changedv0.15.3Aug 19, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```
addedInput schema / properties / app_id / title
```
Added value: +"App Id"
```
addedInput schema / properties / department_id / title
```
Added value: +"Department Id"
```
addedInput schema / properties / geo_id / title
```
Added value: +"Geo Id"
```
addedInput schema / properties / location_id / title
```
Added value: +"Location Id"
```
addedInput schema / properties / metric_name / title
```
Added value: +"Metric Name"
```

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 / title

Added value: +"zdx_get_application_metricArguments"

Changed17 schema fields changedv0.14.0Jul 28, 2026

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

removedInput schema / properties / app_id / description

Removed value: -"The unique ID for the ZDX application."

removedInput schema / properties / app_id / title
```
Removed value: -"App Id"
```
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 / 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 / metric_name / description

Removed value: -"The name of the metric to return. Available values: 'pft' (Page Fetch Time), 'dns' (DNS Time), 'availability'."

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

addedInput schema / properties / query

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "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 / 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 / title

Removed value: -"zdx_get_application_metricArguments"

changedOutput schema / (root)

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

First observedv0.12.7Jun 24, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover read-only safety, and the description adds useful behavior beyond that: one series per metric, datapoints over the `since` HOURS window, default 2h, and the metric names. 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?

Four compact sentences deliver purpose, read-only status, return shape, default window, optional filtering, and the prerequisite app_id source. No filler or redundant restatement.

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?

There is no output schema, but the description explains the return shape: one series per metric with datapoints over the `since` window. It covers the required `app_id`, the key optional `metric_name`, and the time window, making the tool safely invocable despite missing optional filter details.

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 only 14%, so the description must compensate. It adds meaning for `since` (HOURS window, default 2h), `metric_name` (Page Fetch Time, DNS Time, availability), and `app_id` (source tool), but it does not clarify `geo_id`, `location_id`, or `department_id`.

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 begins with a specific verb+resource: 'Get ZDX performance metrics for one application (time-series).' It further names the return series (Page Fetch Time, DNS Time, availability) and the required app association, distinguishing it from sibling tools like zdx_get_application_score_trend.

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?

It gives clear operational guidance: 'Use `app_id` from `zdx_list_applications`' and 'Pass `metric_name` to narrow to a single metric.' It lacks explicit when-not-to-use or alternative tool comparisons, 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_get_application_metric

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools