Deploy the Vault Radar MCP server

Deploy the Vault Radar model context protocol (MCP) server in a Docker container on your local workstation. The Vault Radar MCP server connects to a client so that your LLM can use the data from your HCP Vault Radar instance to answer questions. Refer to the overview for additional information about the Vault Radar MCP server.

Beta feature

This feature is currently available as beta. The beta functionality is stable but possibly incomplete and subject to change. We strongly discourage using beta features in production.

Overview

Complete the following steps to deploy the Vault Radar MCP server:

Pull the Docker image
Connect your client to the MCP server
Configure your client

Prerequisites

Docker Engine v20.10.21+ or Docker Desktop v4.14.0+

Clients

The Vault Radar MCP server supports the following clients:

Authentication

The MCP server requires authentication to access HCP Vault Radar APIs. Create a service principal for your HCP project with viewer role and create service principal keys.

Enable MCP in your client

Refer to your client's documentation for instructions on enabling MCP:

Install the server

The Vault Radar MCP server is available as a Docker image. You can pull the image from the Docker Hub repository. Or you can download the binary and run the server manually.

Create an mcp.json file in the .vscode or .cursor directory of your local workspace and add the following configuration:

{
    "mcp": {
        "servers": {
            "vault-radar": {
                "command": "docker",
                "args": [
                    "run",
                    "--rm",
                    "-i",
                    "-e", "HCP_PROJECT_ID=<HCP Project ID>",
                    "-e", "HCP_CLIENT_ID=<HCP Service Principal Client ID>",
                    "-e", "HCP_CLIENT_SECRET=<HCP Service Principal Client Secret>",
                    "hashicorp/vault-radar-mcp-server:<tag>",
                ]
            }
        }
    }
}

You can configure an MCP server for all the workspaces by updating user settings and adding the following configuration to your settings.json file:

{
    "mcp": {
        "servers": {
            "vault-radar": {
                "command": "docker",
                "args": [
                    "run",
                    "--rm",
                    "-i",
                    "-e", "HCP_PROJECT_ID=<HCP Project ID>",
                    "-e", "HCP_CLIENT_ID=<HCP Service Principal Client ID>",
                    "-e", "HCP_CLIENT_SECRET=<HCP Service Principal Client Secret>",
                    "hashicorp/vault-radar-mcp-server:<tag>",
                ]
            }
        }
    }
}

See VS Code MCP server documentation for more details.

Create an mcp.json file and add the following configuration:

{
    "mcpServers": {
        "vault-radar": {
            "command": "docker",
            "args": [
                    "run",
                    "--rm",
                    "-i",
                    "-e", "HCP_PROJECT_ID=<HCP Project ID>",
                    "-e", "HCP_CLIENT_ID=<HCP Service Principal Client ID>",
                    "-e", "HCP_CLIENT_SECRET=<HCP Service Principal Client Secret>",
                    "hashicorp/vault-radar-mcp-server:<tag>",
            ]
        }
    }
}

See Claude Desktop Users documentation for more details.

Configure your MCP client

Open the chat interface and choose Agent from the mode settings.
Click the tools icon to verify that the Vault Radar MCP server tools are enabled.

Next steps

After downloading the Vault Radar MCP server and connecting it to your client, you can begin prompting your model about your Vault Radar configuration code.

Refer to prompt an AI model documentation for more information.