CAST MCP Server for Gatekeeper installation on Microsoft Windows


Overview

This guide covers the installation of the CAST MCP Server for Gatekeeper on Microsoft Windows. It’s intended for:

  • Direct installation on Microsoft Windows
  • new installations (i.e. from scratch)
  • in-place updates to a new release

The installation package com.castsoftware.gatekeeper.mcpserver external link includes an installation script (.bat file), various configuration files and the binaries themselves.

What’s new?

See the release notes.

How it works

The MCP Server sits between an AI client and the CAST Imaging for Gatekeeper REST API:

  1. A user types a natural-language query in their AI assistant (e.g., “Show me security violations for MyApp”).
  2. The AI client (Claude / Copilot) identifies the right MCP Tool to call.
  3. The MCP Server receives the structured tool call, validates inputs, and forwards the request to the API.
  4. The response is normalised and returned to the AI, which presents a human-readable summary.

The diagram below shows where the MCP Server for Gatekeeper sits in the CAST Imaging platform, and the trust boundaries between your AI tooling and CAST. Your MCP-aware client reaches it through the CAST Imaging public gateway on the /mcp/gatekeeper route, and it reads from the Gatekeeper REST API only. The diagram also shows the CAST Imaging MCP Server, which can be installed alongside it.

Requirements

The CAST MCP Server for Gatekeeper is a standalone component and can be installed wherever convenient in your environment, e.g. on a dedicated machine, or on a machine already used by other CAST Imaging components.

When using a dedicated machine, CAST recommends following the general hardware and software requirements but note that the component does not require:

  • a Java JRE/JDK

Other requirements:

  • MCP Server runs as a Microsoft Windows service on TCP port 8283 (configurable). You may need to adjust firewall rules to allow incoming connections to this port.
  • see software requirements for more information about supported Microsoft Windows OS versions
  • a minimum of 2GB free disk space
  • An MCP-aware client such as GitHub Copilot (Visual Studio Code), Claude Desktop, or Cursor
  • a functioning release of CAST Imaging for Gatekeeper (Dashboards) installed (MCP Server interacts with the imaging-services component) in your network (see CAST Imaging compatibility below)
  • a CAST Imaging API key, see Generating an API key.
    Available in ≥ 3.6.6-funcrel
    Alternatively, Claude Code and Visual Studio Code can sign in through the browser using OAuth - see Authenticate MCP clients with OAuth

CAST Imaging compatibility

MCP Server release Required API version/CAST Imaging release
≥ 3.0.0-funcrel ≥ 3.6.4-funcrel
≥ 3.0.0-beta1 ≥ 3.6.2-funcrel

MCP-aware client connection routing

MCP-aware clients connect directly to CAST Imaging via its public gateway - instead of direct to the MCP Server. As a result, CAST Imaging 3.6.2-funcrel or later is required as the target installation to ensure proper routing back to the MCP Server. This integration ensures all query requests are routed through CAST Imaging.

HTTPS

If you require a secure HTTPS connection between your MCP-aware client and the MCP Server, you must enable HTTPS on the CAST Imaging gateway - see HTTPS configuration.

Installation process

Step 1 - Verify connection to CAST Imaging

Before proceeding, ensure you can access CAST Imaging (the imaging-services component) from the machine where you intend to install MCP Server by running the following (tailored to your own environment):

$ curl -H "x-api-key: <your-imaging-api-key>" http://<your_imaging_public_URL>:8090/dashboards/rest/

The expected output is at least one entry similar to:

[
  {
    "href": "55c46218-c3f3-44ad-9042-7e1791ec7cbf",
    "name": "55c46218-c3f3-44ad-9042-7e1791ec7cbf",
    "dbType": "ADG",
    "version": "8.4.10",
    "schema": "app1_central",
    "dbmsVersion": "PostgreSQL",
    "componentsIndexStatus": "upToDate",
    "violationsIndexStatus": "toCreate",
    "systems": {
      "href": "55c46218-c3f3-44ad-9042-7e1791ec7cbf/systems",
      "name": "All Systems. A system represents a portfolio of applications."
    },
    "applications": {
      "href": "55c46218-c3f3-44ad-9042-7e1791ec7cbf/applications",
      "name": "All Applications. An application represents ..."
    },
    "nbOfApplications": 1,
    "configurations": {
      "href": "55c46218-c3f3-44ad-9042-7e1791ec7cbf/configuration/snapshots",
      "name": "All configuration snapshots ..."
    },
    "results": {
      "href": "55c46218-c3f3-44ad-9042-7e1791ec7cbf/results",
      "name": "Results by snapshots, by systems, by ..."
    },
    "commonCategories": null,
    "tags": null
  }
]

Step 2 - Download the installation media

Download the latest release of the installer (com.castsoftware.gatekeeper.mcpserver external link) and unzip it anywhere on your local disk. The following files/folders will be created:

com.castsoftware.gatekeeper.mcpserver.<version>/
├── gatekeeper-mcpserver
├── tools
├── CLAUDE.md
├── configuration.conf
├── copilot-instructions.md
├── cursor-rules.mdc
├── GEMINI.md
├── INSTALLER_BUILD_GUIDE.md
├── mcp-server-installer.bat
└── README.md

Step 3 - Configure your installation

Locate the configuration.conf file at the root of the unzipped installation media. Open the file with a text editor and update the following settings to match your environment - the other settings can be left at their defaults:

HOST_CONTROL_PANEL=<imaging-services-machine>
PORT_CONTROL_PANEL=8098
MCP_SERVER_PORT=8283
INSTALL_DIR=C:\Program Files\Cast\Gatekeeper-MCP-Server
CONFIG_DIR=C:\ProgramData\CAST\Gatekeeper-MCP-Server
SERVICE_NAME="GatekeeperMCPServer"
SERVICE_HOST=<mcp-server-machine>
CONTROL_PANEL_SSL_ENABLED=false
TELEMETRY_ENABLED=true
TELEMETRY_LOCAL_FILE=C:\ProgramData\CAST\Gatekeeper-MCP-Server\logs\telemetry\telemetry.jsonl
SSL_CA_BUNDLE=

Setting Description
HOST_CONTROL_PANEL Required: IP address/hostname/FQDN of the machine on which the CAST Imaging imaging-services component is installed. The use of localhost is not supported.
PORT_CONTROL_PANEL Port on which the CAST Imaging Control Panel service (part of the imaging-services component) is running - unless you have changed it during the CAST Imaging installation, leave it as is.
MCP_SERVER_PORT MCP Server listening port, 8283 by default.
INSTALL_DIR Installation location.
CONFIG_DIR Location of the configuration files and logs.
SERVICE_NAME Name under which the MCP Server registers with the CAST Imaging Control Panel. Do not change it.
SERVICE_HOST Required: IP address/hostname/FQDN of the machine on which the MCP Server will be installed (i.e. the current machine). Do not set as localhost.
CONTROL_PANEL_SSL_ENABLED Set to true to communicate with a CAST Imaging instance configured to use HTTPS.
TELEMETRY_ENABLED Records MCP tool calls in a local telemetry log, true by default.
TELEMETRY_LOCAL_FILE Location of the local telemetry log.
TELEMETRY_PUSH_ENABLED Periodically pushes the local telemetry log to CAST, true by default. Not present in the shipped file: add the line to change it.
TELEMETRY_PUSH_INTERVAL_MINUTES Interval between two pushes, 120 minutes by default. Not present in the shipped file: add the line to change it.
SSL_CA_BUNDLE Path to a certificate chain in Base-64 PEM format. It can be set here or after the installation. Only necessary where CAST Imaging is configured in HTTPS mode with SSL/TLS certificates issued by a private or self-signed certificate authority (CA) - see HTTPS with self-signed or private CA certificates.

Step 4 - Run the installation

Open a CMD window with elevated permissions (right click, Run as administrator) and execute the following command from the root of the unzipped files:

mcp-server-installer.bat --install configuration.conf

Wait for the installation process to complete. On completion, check that a Microsoft Windows service named Gatekeeper-MCP-Server (display name CAST Gatekeeper MCP Server) has been created and is up and running.

Verify the health endpoint of the MCP Server:

$ curl http://<mcp-server>:8283/mcp/healthcheck

Expected response:

{"status": "healthy", "service": "GatekeeperMCPServer"}

Step 5 - Connect your AI client

Configure each AI client to connect through CAST Imaging, not to the MCP Server directly - see Connect your AI client. It covers GitHub Copilot, Claude Code, Cursor, OpenAI Codex, Gemini CLI and Claude Desktop, with API key or OAuth sign-in.

Step 6 - Test the connection

From an AI client, ask Show me the compliance status for <APP_NAME>. If you get an answer, the MCP Server is working. Otherwise, see Test your connection and Update and troubleshoot.

Next steps