zscaler-mcp-server

Official

by zscaler

Overview Schema Source Related Servers Discussions Admin

Python

Hybrid

zins_get_firewall_by_action

Read-only

Get Zero Trust Firewall traffic grouped by action (allow/block). Read-only analytics.

Instructions

Get Zero Trust Firewall traffic grouped by action (allow/block). Read-only analytics.

One row per action with its aggregated total — the allowed-vs-blocked split. Window must be a 7- or 14-day historical interval.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	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.
`end_time`	No
`start_time`	No
`end_days_ago`	No
`start_days_ago`	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 / end_days_ago / title
```
Added value: +"End Days Ago"
```
addedInput schema / properties / end_time / title
```
Added value: +"End Time"
```
addedInput schema / properties / limit / title
```
Added value: +"Limit"
```

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 / start_days_ago / title
```
Added value: +"Start Days Ago"
```
addedInput schema / properties / start_time / title
```
Added value: +"Start Time"
```

addedInput schema / title

Added value: +"zins_get_firewall_by_actionArguments"

Changed14 schema fields changedv0.14.0Jul 28, 2026

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

removedInput schema / properties / end_days_ago / description

Removed value: -"Days ago for end. Default: 2. Interval = start - end must be 7 or 14."

removedInput schema / properties / end_days_ago / title
```
Removed value: -"End Days Ago"
```

removedInput schema / properties / end_time / description

Removed value: -"ALTERNATIVE: End time as Unix epoch in MILLISECONDS."

removedInput schema / properties / end_time / title
```
Removed value: -"End Time"
```

removedInput schema / properties / limit / description

Removed value: -"Maximum number of action entries to return (1-1000)."

removedInput schema / properties / limit / title
```
Removed value: -"Limit"
```

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 / start_days_ago / description

Removed value: -"Days ago for start. Default: 9 (7-day interval). API needs 7 or 14 day intervals."

removedInput schema / properties / start_days_ago / title
```
Removed value: -"Start Days Ago"
```

removedInput schema / properties / start_time / description

Removed value: -"ALTERNATIVE: Start time as Unix epoch in MILLISECONDS."

removedInput schema / properties / start_time / title
```
Removed value: -"Start Time"
```

removedInput schema / title

Removed value: -"zins_get_firewall_by_actionArguments"

changedOutput schema / (root)

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

First observedv0.12.7Jun 24, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint: true and openWorldHint: false. The description adds that it is read-only analytics, matches the annotation, and provides additional behavioral context: the output structure (one row per action) and the window constraint. This goes beyond annotations without contradicting them.

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, densely packed with the core purpose, output format, and a critical constraint. It is front-loaded with the action, has no filler, and every sentence provides value.

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 tool with 6 parameters and no output schema, the description gives the essential output (one row per action) and a critical window constraint, but it omits details about the time parameters, pagination, and the meaning of the returned fields. The query parameter is well-documented in the schema, but the other parameters remain vague. The description is adequate but leaves gaps that could be filled.

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 17% (only the 'query' parameter has a description). The description adds a key constraint on the time window (must be 7- or 14-day) but does not explicitly explain any of the time-related parameters (start_time, end_time, start_days_ago, end_days_ago) or the 'limit' parameter. It provides some compensation for the low coverage but is incomplete.

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 clearly states the tool retrieves Zero Trust Firewall traffic grouped by action, and specifies the output as one row per action with aggregated totals. It uses a specific verb ('get'), resource ('Zero Trust Firewall traffic'), and grouping ('by action'), which distinguishes it from sibling tools like zins_get_firewall_by_location.

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 implies usage for analyzing allow/block splits in firewall traffic and explicitly constrains the time window to 7- or 14-day intervals. It does not explicitly name alternatives or state when not to use, but the purpose is clear and the constraint provides practical guidance.

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

Deploy Server

zins_get_firewall_by_action

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools