Skip to main content
Glama
zscaler

zscaler-mcp-server

Official
by zscaler

zia_list_cloud_app_control_actions

Read-only

Lists available Cloud App Control actions for a given cloud application, automatically resolving its category to return the full action set. Handles API edge cases by probing other apps in the same category.

Instructions

List the granular Cloud App Control (CAC) actions available for a cloud application — answers 'what actions can I control for ?', 'list actions for Azure DevOps', 'what can I block on Dropbox', 'show me available actions for ChatGPT'. Takes a single cloud_app (canonical enum like AZURE_DEVOPS or friendly name like 'Azure DevOps'); the tool auto-resolves the name, looks up its category (rule type), and returns the category's full action set. Actions are CATEGORY-LEVEL not per-app — every app in SYSTEM_AND_DEVELOPMENT shares the same actions, every app in AI_ML shares its own set, etc. The tool also handles a ZIA API quirk where calling list_available_actions(rule_type, [some_app]) sometimes returns empty because not every app is a 'representative' for its category — when that happens, it transparently walks other apps in the same category until one surfaces the action set. Returns a dict with: cloud_app, resolved_app, category, category_name, actions, actions_surfaced_via (which app finally produced the actions), and probe_attempts. Use the optional rule_type parameter only to override the auto-detected category; use query (JMESPath) to project just the actions list (e.g. 'actions') or filter them (e.g. 'actions[?contains(@, BLOCK)]').

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cloud_appYesThe cloud application the user is asking about. Accepts the canonical ZIA enum (``AZURE_DEVOPS``, ``DROPBOX``, ``CHATGPT_AI``) **or** a friendly display name (``'Azure DevOps'``, ``'dropbox'``, ``'chatgpt'``). The tool resolves the input to its canonical form, looks up the app's category (= rule type), and returns the granular action vocabulary the API supports for Cloud App Control rules in that category. The action vocabulary is *surfaced* at the category level — every app in a category resolves to the same returned list — but the create endpoint validates per (rule_type, application, action) tuple and can still reject a category-level action when paired with a specific app. Treat the returned list as a superset; the create call is the only authoritative validator.
rule_typeNoOptional override for the rule-type category. By default the tool infers the rule type from ``cloud_app``'s ``parent`` field in the policy catalog. Only set this when you want to force a specific category (e.g. when ZIA classifies an app under one category but you want actions for a different one). Must be one of the canonical category enums (``AI_ML``, ``WEBMAIL``, ``FILE_SHARE``, ``SYSTEM_AND_DEVELOPMENT``, ``STREAMING_MEDIA``, ``SOCIAL_NETWORKING``, ``INSTANT_MESSAGING``, ``BUSINESS_PRODUCTIVITY``, ``ENTERPRISE_COLLABORATION``, ``SALES_AND_MARKETING``, ``CONSUMER``, ``HOSTING_PROVIDER``, ``IT_SERVICES``, ``HUMAN_RESOURCES``, ``LEGAL``, ``HEALTH_CARE``, ``FINANCE``, ``DNS_OVER_HTTPS``, ``CUSTOM_CAPP``).
queryNoOptional JMESPath expression applied to the response. Useful for projecting just the actions list (``actions``) or filtering them (``actions[?contains(@, 'BLOCK')]``).
serviceNoThe service to use.zia
Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses important behavioral details: actions are category-level, the tool handles ZIA API quirks by walking apps to find actions, and the create call is the final validator. This adds significant value.

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

Conciseness4/5

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

The description is detailed but well-structured, with example questions upfront. It efficiently conveys purpose, behavior, and parameter usage without unnecessary redundancy. Could be slightly more concise, but still effective.

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

Completeness5/5

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

Despite no output schema, the description fully explains the return value (dict with seven fields) and covers edge cases like empty results and auto-resolution. It is complete for the tool's complexity.

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 100%, so baseline is 3. The description adds extra semantic context for cloud_app (resolution, category inference), rule_type (override purpose), and query (JMESPath examples), pushing the score to 4.

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 explicitly states the tool lists granular Cloud App Control actions for a cloud application, with example user queries. It distinguishes from sibling tools by focusing on actions rather than rules or policies.

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?

Provides clear guidance on when to use the tool (answering action-related questions) and how to use optional parameters (rule_type override, query filtering). However, it doesn't explicitly state when not to use it or mention alternative tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zscaler/zscaler-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server