Skip to main content

Zscaler Workload Segmentation MCP server

Zscaler Workload Segmentation provides identity-based microsegmentation for workloads across data centers and clouds. An MCP server for Workload Segmentation allows AI agents to discover application dependencies, create zero trust policies, simulate policy changes safely, and prevent lateral movement without needing direct console access.

Setting up an MCP server

This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the Authentication section on this page.

Before you begin

You'll need:

  • Access to AI Gateway with permission to create MCP servers.
  • API credentials for the application you're connecting (see the Authentication section on this page for what to collect).

Create an MCP server

Find the app in the catalog

  1. Sign in to AI Gateway and select App Catalog from the left navigation.
  2. Search for the application you want to connect, then select it from the catalog.
  3. Select Create MCP Server to start the wizard.

App Configuration

Confirm the Base URL for the API, then, under Tools, select the endpoints you want to expose. Select Next.

MCP Server Setup

  1. Enter a Name for your server — something descriptive that identifies both the application and its purpose.
  2. Enter a Description so your team knows what the server is for.
  3. Set the log level: choose Production Mode for terser logs, or Non-Production Mode for more verbose logs that can help with debugging.
  4. Select Next.

Authentication

Enter the authentication details for the application. This varies by service — see the Authentication section on this page for the specific credentials, OAuth URLs, and scopes to use.

Review

Look over the summary of your MCP server configuration, then select Create & Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.


Connect to an AI client

Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:

Tips

  • You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
  • If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.

Authentication

Zscaler Workload Segmentation uses API key authentication.

ValueSetting
Base URLhttps://api.workload.zscaler.com
API key headerX-API-Key
Scopeshttps://api.workload.zscaler.com

Available tools

The tools enable workload discovery and identity management, application dependency mapping, policy creation and simulation, traffic analytics, and compliance reporting. They help you build zero trust policies, test policy changes safely before enforcement, detect anomalous traffic, and prove compliance with segmentation requirements.

ToolDescription
Workload DiscoveryDiscover all workloads, identify unprotected services, find dependencies, map topology
Workload IdentityCreate workload identities, tag by tier, group by business unit, classify by data sensitivity
FingerprintingGenerate workload fingerprints, verify identity, track changes, monitor drift
Dependency DiscoveryMap application communications, discover service dependencies, identify data flows, track API calls
Topology VisualizationShow application topology, display traffic patterns, highlight critical paths, map east-west traffic
Policy CreationCreate zero trust policies, build allow lists, define service boundaries, set communication rules
Policy TemplatesApply PCI compliance templates, use three-tier app templates, deploy microservices policies
Granular ControlsControl by port and protocol, restrict by process, limit by user context, filter by metadata
Policy SimulationSimulate policy changes, preview blocked connections, test before deployment, validate rules
Impact AssessmentShow affected workloads, calculate disruption risk, identify dependencies, measure blast radius
Safe DeploymentStage policy rollout, monitor mode first, gradual enforcement, rollback capability
Flow AnalysisShow traffic patterns, monitor data volumes, track connection counts, analyze protocols
Anomaly DetectionDetect unusual traffic, find policy violations, identify new connections, monitor behavioral changes
Performance MetricsMeasure latency impact, track throughput, monitor connection health, assess overhead
Lateral Movement PreventionBlock unauthorized connections, prevent service hopping, stop attack propagation
Compliance ReportsGenerate compliance reports, document segmentation, prove policy enforcement, track changes
CI/CD IntegrationIntegrate with Jenkins, support GitOps, infrastructure as code, policy as code

Tips

Test policy changes in simulation mode first and review the impact assessment before enforcing any policy in production.

Deploy policies gradually in monitor mode to establish a baseline.

Enable enforcement once you're confident the rules won't disrupt legitimate traffic.

Define clear role-based access controls for who can create policies.

Enable monitoring and alerting on all policy changes to track who made modifications and when.