ControlUp MCP Server

The ControlUp Model Context Protocol (MCP) Server provides a standard interface for integrating your AI agents with ControlUp products. MCP enables AI agents to invoke product-specific tools and operations in a structured and consistent way. If you are already using any AI agent, like Microsoft Copilot, Cursor.io or Claude Code, you can connect these AI agents to our MCP server to provide access to ControlUp information within your own AI agent.

ControlUp MCP provides a unified MCP server for all supported ControlUp products and modules. You can selectively enable tools for the specific products you intend to use to more efficiently enable your AI agent to interact with ControlUp.

What is an MCP Server?

An MCP server is a long-running process that exposes a set of product-specific tools over the MCP protocol. AI agents use this interface to perform context-aware actions without manual API integration.

Our MCP servers:

• Expose tools for ControlUp products, such as ControlUp for VDI, ControlUp for Desktops, Compliance, Workflows, etc.

• Support selective product enablement

• Communicate with AI agents via standard transports (for example stdio, HTTP)

• Use customer credentials for authentication

Benefits

• Unified integration: One MCP supports all ControlUp products.

• Selective tooling: Only enabled product tools are exposed to the agent.

• Scalable workflows: Tools can be composed in a single prompt session.

• Consistent developer experience: Same protocol across products.

Security Considerations

ControlUp MCP runs locally and uses customer credentials (such as API keys) to authenticate and perform operations on behalf of your AI agent.

When used with a public LLM provider, data sent through the MCP may be exposed to that provider. This would be the same as manually pasting sensitive data into a public AI service.

Before using the ControlUp MCP server with your AI agent, you must review the data policies of your chosen AI agent provider.

Important!

We recommend that you do not connect a public AI agent that is not specifically licensed to your company with our MCP server. If you do, sensitive information, for example user data and API keys, can potentially become available to all users of that AI agent.

ControlUp MCP - Get Started

Every user who wants to connect to the ControlUp MCP server must perform these steps locally on their AI agent.

Prerequisites

Ensure you have the following:

• Node.js 18+ installed where the MCP server runs.

• A supported AI agent capable of launching and communicating with MCP servers. We strongly recommend using only privately licensed AI agents.

• A ControlUp API Key and your Organization ID, also available from the API Key Management popup.

Step 1: Configure the MCP Server

Each user must open the relevant AI agent’s settings and dd the appropriate configuration as described below to the AI agent’s MCP settings file. This file is usually called:  mcp.json and is available from the settings menu in most AI agents. Add the following JSON commands anywhere in that settings file.

Option A: Standard configuration (enables all ControlUp products)

Use this configuration to automatically enable tools for all supported ControlUp products. This is the recommended default.

JSON

{
  "controlup": {
    "type": "stdio",
    "command": "npx",
    "args": [
      "-y",
      "@controlup-ai/mcp@latest"
    ],
    "env": {
      "API_KEY": "YOUR_API_KEY",
      "ORG_ID": "YOUR_ORG_ID",
    }
  }
}

• Automatic installation: You do not need to install the package manually. The npx command fetches and runs the latest version of @controlup-ai/mcp when the agent starts.

• Credentials: Replace YOUR_API_KEY and YOUR_ORG_ID with your actual ControlUp values.

Option B: Advanced configuration (filter specific products)

If you want to load tools only for specific ControlUp products, add the DOMAINS environment variable with a comma-separated list of product identifiers with quotation marks around the list. Here is an example of the JSON that includes DEX Platform, ControlUp for Desktops, ControlUp for VDI:

JSON

{
  "controlup": {
    "type": "stdio",
    "command": "npx",
    "args": [
      "-y",
      "@controlup-ai/mcp@latest"
    ],
    "env": {
      "API_KEY": "YOUR_API_KEY",
      "ORG_ID": "YOUR_ORG_ID",
      "DOMAINS": "platform,cu4d,vdi"
    }
  }
}

Product selection (optional):

• If omitted: The server initializes tools for all products (see Option A).

• If specified: The server initializes tools only for the listed products per the table below.

Step 2 - Start the Agent

1. Save your JSON configuration in your AI agent settings.

2. Restart your AI agent.

3. Confirm that the MCP server starts and the tools for the enabled products appear in your list of MCP servers.

Your agent should display log entries indicating MCP startup and tool discovery.

Example Interaction

Once the ControlUp MCP server is configured, you can make an AI agent that may invoke multiple tools. Here is an example:

“Summarize audit log entries for the past 24 hours.”

The AI agent can combine various product tools to answer this request.

Troubleshooting