Illumio

You can use Illumio MCP Server to programmatically manage Illumio PCE data, including workloads, labels, and traffic analysis, all through MCP-compatible clients. It enables automated interactions with your PCE from your preferred tooling and prompts, streamlining security posture and workload management tasks.

How to use

Connect to the Illumio MCP Server from an MCP client to perform common tasks like creating or updating workloads and labels, querying traffic flows, and running health checks on your PCE. Use available prompts or endpoints to manage resources and pull analytics. When you run prompts, ensure your client is configured to reach one of the MCP server endpoints and that you have valid PCE credentials loaded.

Typical usage patterns include:

• Managing workloads (create, update, delete) and associating labels to workloads
• Reading all labels and applying them to workloads or rules
• Fetching traffic flow data and traffic summaries for analysis and security assessments
• Verifying connectivity and health of the PCE connection These actions are exposed through the MCP interface so you can automate workflows and integrate Illumio data into your dashboards and automation pipelines.

How to install

# Prerequisites
python3.8+

# Step 1: Clone the MCP server repository
# Use your actual repository path if you are forking or configuring locally
# Example placeholder path
git clone [repository-url]
cd illumio-mcp

# Step 2: Install Python dependencies
pip install -r requirements.txt

Additional configuration and usage notes

Configure how you run the MCP server to suit your environment. You can run it using uv for local development and background execution, or run it in Docker for containerized deployments. Environment variables you provide should include your PCE host, port, organization ID, and API credentials.

Claude Desktop and MCP integration can be used to simplify prompt handling. You place the MCP config in Claude’s custom settings under the mcpServers section, including the command, args, and environment you need for the session.

Configuration and examples

Two example configuration methods are provided here. Use the one that suits your environment.

{
  "mcpServers": {
    "illumio-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/alex.goller/git/illumio-mcp",
        "run",
        "illumio-mcp"
      ],
      "env": {
        "PCE_HOST": "your-pce-host",
        "PCE_PORT": "your-pce-port",
        "PCE_ORG_ID": "1",
        "API_KEY": "api_key",
        "API_SECRET": "api_secret"
      }
    }
  }
}

Docker deployment and Claude Desktop integration

You can run the MCP server in a Docker container or configure Claude Desktop to launch the container for you. The configuration examples below show the required environment wiring and how to pass credentials securely.

{
  "mcpServers": {
    "illumio-mcp-docker": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--init",
        "--rm",
        "-v",
        "/Users/YOUR_USERNAME/tmp:/var/log/illumio-mcp",
        "-e",
        "DOCKER_CONTAINER=true",
        "-e",
        "PYTHONWARNINGS=ignore",
        "--env-file",
        "/Users/YOUR_USERNAME/.illumio-mcp.env",
        "illumio-mcp:latest"
      ]
    }
  }
}

Available tools

get-workloads

Retrieve all workloads from the PCE

create-workload

Create an unmanaged workload with specified name, IP addresses, and labels

update-workload

Update an existing workload's properties

delete-workload

Remove a workload from PCE by name

create-label

Create a new label with key-value pair

delete-label

Remove an existing label by key-value pair

get-labels

Retrieve all labels from PCE

get-traffic-flows

Get detailed traffic flow data with filtering options such as date range, source/destination, service, and workload lists

get-traffic-flows-summary

Get summarized traffic flow information with the same filtering options as get-traffic-flows

get-rulesets

Get rulesets from the PCE with optional filtering by name or enabled status

get-iplists

Get IP lists from the PCE with optional filtering by name/description/IP ranges

check-pce-connection

Verify PCE connectivity and credentials

get-events

Get events from the PCE with filtering by type, severity, status, and limit