Umbraco

Provides MCP access to the Umbraco Management API for AI-assisted back office tasks.

typescript

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "umbraco-umbraco-cms-mcp-dev": {
      "command": "npx",
      "args": [
        "@umbraco-cms/mcp-dev@17"
      ],
      "env": {
        "UMBRACO_BASE_URL": "https://localhost:port",
        "UMBRACO_CLIENT_ID": "YOUR_API_USER_ID",
        "UMBRACO_CLIENT_SECRET": "YOUR_API_SECRET",
        "NODE_TLS_REJECT_UNAUTHORIZED": "0",
        "UMBRACO_INCLUDE_TOOL_COLLECTIONS": "document,media,document-type,data-type"
      }
    }
  }
}

You unlock AI-powered content management by connecting your AI agent to Umbraco through an MCP server. This server provides secure, permission-based access to Umbraco’s Management API, enabling back office tasks to be performed via natural conversation without navigating the UI.

How to use

This MCP server is designed to be used with an MCP client such as Claude Desktop. After you configure the server, you can instruct your AI agent to manage Umbraco content, media, and meta-data using natural language commands. The server authenticates with an Umbraco API user, so your permissions strictly govern what the agent can do within Umbraco.

To connect, supply the MCP server’s credentials and endpoint details to your MCP client. The server uses your Umbraco API user credentials to obtain access tokens and perform operations through the Management API. You control access by configuring the API user’s roles and permissions in Umbraco.

How to install

Prerequisites: you need Node.js installed on your machine. You also need an Umbraco API user with appropriate permissions and the ability to access your Umbraco instance from the machine running the MCP client.

Create an Umbraco API user with the required permissions in your Umbraco instance.
Install and run the MCP client configuration using the following setup in your client configuration file at claude_desktop_config.json.

{
  "mcpServers": {
    "umbraco-mcp": {
      "command": "npx",
      "args": ["@umbraco-cms/mcp-dev@17"],
      "env": {
        "NODE_TLS_REJECT_UNAUTHORIZED": "0",
        "UMBRACO_CLIENT_ID": "your-api-user-id",
        "UMBRACO_CLIENT_SECRET": "your-api-secret",
        "UMBRACO_BASE_URL": "https://localhost:{port}",
        "UMBRACO_INCLUDE_TOOL_COLLECTIONS": "document,media,document-type,data-type"
      }
    }
  }
}

Additional configuration and security notes

The following environment variables are used by the MCP server to authenticate and locate the Umbraco instance. They must be defined in your MCP client configuration and are included in the server’s runtime environment.

NODE_TLS_REJECT_UNAUTHORIZED: 0 to allow self-signed certificates during local development.
UMBRACO_CLIENT_ID: Your Umbraco API user ID.
UMBRACO_CLIENT_SECRET: Your Umbraco API user secret.
UMBRACO_BASE_URL: The base URL of your Umbraco instance, including the port if necessary.
UMBRACO_INCLUDE_TOOL_COLLECTIONS: Comma-delimited list of tool collections to expose to the AI agent.

Available tools

rulesync

Generates instruction files for AI tooling integration, helping maintain consistency with development patterns across multiple AI tools.

claude_desktop_config

Configuration structure used to wire an MCP server into Claude Desktop, including command, arguments, and environment variables.

Built by

VeilStrat

AI signals for GTM teams