agentmods.dev

zscaler-mcp-server: Instructions file for Gemini CLI

GEMINI.md

zscaler-mcp-server GEMINI.md is an instructions file for Gemini CLI from zscaler/zscaler-mcp-server. It costs 2,152 tokens per session, scanned A, original, MIT.

Instructions for using tools that manage Zscaler’s Zero Trust Exchange, a security platform for controlling access, internet traffic, devices, applications, and related data.

In plain words
What is it for?
Use them when querying or changing Zscaler services such as ZPA, ZIA, ZDX, ZCC, EASM, or ZIdentity, while following the required activation and read-only rules.
Why use it?
They explain how to find the right service tools, authenticate, and complete staged ZIA changes so updates take effect.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md. Also seen: mentions Claude Code; mentions Gemini CLI.

This is zscaler/zscaler-mcp-server's own configuration. It tells Gemini CLI how to work on zscaler-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zscaler-mcp-server configures →

not rated 50repo yesterday A scan 2,152 tokens original MIT
View source ↗ zscaler/zscaler-mcp-server pypi.org
Reuse

Borrowing it

Nothing to install: this file belongs to zscaler/zscaler-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zscaler/zscaler-mcp-server/master/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/zscaler/zscaler-mcp-server

Made for: Gemini CLI.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for zscaler-mcp-server GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zscaler/zscaler-mcp-server/gemini-md.svg)](https://agentmods.dev/instructions/zscaler/zscaler-mcp-server/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/zscaler/zscaler-mcp-server/gemini-md"><img src="https://agentmods.dev/badge/instructions/zscaler/zscaler-mcp-server/gemini-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,152 This file is loaded in full into every session.
When invoked 2,152 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.02152 $0.02152
Opus 5 $0.01076 $0.01076
Sonnet 5 $0.00430 $0.00430
Haiku 4.5 $0.00215 $0.00215

Measured 8d ago against content hash c8c5eded2d64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

zscaler-mcp-server GEMINI.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

GEMINI.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zscaler MCP Server

254 read tools (plus write tools, off by default) for managing the Zscaler Zero Trust Exchange. Services: ZPA, ZIA, ZDX, ZCC, ZCell, EASM, Z-Insights, ZIdentity, ZTW (Zscaler Workload Segmentation), ZMS (Zscaler Microsegmentation).

Tool Naming & Discovery

All tools follow {service}_{verb}_{resource} naming: zia_list_locations, zpa_create_access_policy_rule, zdx_get_application. Service prefixes: zia_, zpa_, zdx_, zcc_, easm_, zins_, zid_, ztw_. Use the prefix to discover tools for a given service.

Critical Gotchas

  • ZIA requires activation. After any ZIA create/update/delete, call zia_activate_configuration(). Changes are staged until activation. Forgetting this is the #1 source of "my change didn't work" issues.
  • OneAPI is the only supported authentication mode. All tools authenticate via zscaler.ZscalerClient against ZIdentity using the unified ZSCALER_CLIENT_ID / ZSCALER_CLIENT_SECRET (or ZSCALER_PRIVATE_KEY) / ZSCALER_VANITY_DOMAIN / ZSCALER_CUSTOMER_ID (ZPA only) credentials.
  • ZDX is read-only. ZDX tools only query data. There are no create/update/delete operations except for deep traces (zdx_start_deep_trace).
  • ZDX since parameter is in hours, not timestamps. Default is 2 hours. Example: since=24 means "last 24 hours."
  • IDs are strings, even when they look numeric. Always pass IDs as strings.
  • ZPA dependency chain matters. To onboard an application: create app connector group -> create server group (references connector group) -> create segment group -> create application segment (references server and segment groups) -> create access policy rule. Skipping dependencies causes cryptic 400 errors.
  • ZIA dependency chain for locations. To onboard a location: create static IP -> create VPN credential (references static IP) -> create location (references VPN credential and static IP). The location won't work without the traffic forwarding prerequisites.
  • ZIA policy-rule updates are PUT, not PATCH. Every ZIA update_*_rule tool maps to a PUT (full replacement). Tools silently backfill name and order from the existing rule when missing, but other fields omitted from the payload may be reset by the API. Affected: zia_update_ssl_inspection_rule, zia_update_cloud_firewall_dns_rule, zia_update_cloud_firewall_ips_rule, zia_update_file_type_control_rule, zia_update_sandbox_rule.
  • ZIA cloud-application catalogs are NOT interchangeable. Shadow IT analytics catalog (zia_list_shadow_it_apps) uses friendly names + numeric IDs. Policy-engine catalog (zia_list_cloud_app_policy, zia_list_cloud_app_ssl_policy) uses canonical UPPER_SNAKE_CASE enums. Tools that accept friendly names (SSL inspection, file type control, cloud-app control) auto-resolve them and surface the audit in _cloud_applications_resolution.
  • DNS rules use applications, not cloud_applications. The applications field on DNS rules refers to DNS tunnels and network applications — it is not the cloud-app enum catalog and is not auto-resolved.
  • ZIA Sandbox rules vs sandbox reports. zia_*_sandbox_rule tools manage Sandbox policy rules. zia_get_sandbox_* tools (quota, report, behavioral_analysis, file_hash_count) are read-only sandbox reports. Don't confuse the two.

Read the full file on GitHub · 96 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 96 lines · 2,152 tokens per session scan A c8c5eded2d64

Subscribe to this mod's changes

zscaler-mcp-server GEMINI.md is an instructions file published in the GitHub repository zscaler/zscaler-mcp-server (50 stars, last pushed yesterday), licensed MIT. It adds 2,152 tokens to every session, about $0.0108 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Securityaihacktoberfestmcpmcp-serverpypizcc
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens