OfficialVerified

Umbraco Cms Dev MCP Server

Umbraco Management API tasks performed via natural language conversations.

Data last scanned today · Reviewed today

63★ 39TypeScriptMIT

Overview

This MCP server provides a direct interface between AI agents and the Umbraco Management API. It enables automation of back office tasks, allowing users to handle complex content management workflows, document operations, and media handling through natural language inputs instead of manual UI interaction.

Our verdict

This server carries a high-risk rating with a security score of 40/100. Because it is community-maintained rather than official and lacks an editorially reviewed authentication or read-only implementation, users should exercise caution. It is suitable for experimental workflows in development environments but currently lacks the vetting necessary for sensitive production systems.

Supports multiple content entity types like documents and media.
Uses standard Umbraco API user permissions for access control.
Active development with commits within the last 24 hours.
Managed under the permissive MIT open-source license.

Security score is 40/100 due to lack of editorial review.
Authentication mechanisms remain currently unreviewed for vulnerabilities.
Read-only mode implementation has not been audited.
Project lacks an official homepage link for verification.

Setup

Claude Desktop

{
  "mcpServers": {
    "umbraco-cms-mcp-dev": {
      "args": [
        "-y",
        "@umbraco-cms/mcp-dev"
      ],
      "command": "npx"
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

No read-only mode — running this grants full read/write access.
No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Compatibility

Client	Local	Docker	Remote	Read-only
ChatGPT
Claude Desktop
Cursor
VS Code
Windsurf

Frequently asked questions

›How does the server handle security and permissions?

The server uses Umbraco API users for authentication and relies on Umbraco's built-in user permission system to determine what actions the AI agent can perform.

›What Umbraco resources can the AI agent interact with?

The server allows you to define the accessible tools via the UMBRACO_INCLUDE_TOOL_COLLECTIONS environment variable, supporting collections like document, media, document-type, and data-type.

›Can I use this server for multi-tenant Umbraco Cloud deployments?

Yes, by setting UMBRACO_CLOUD_ROUTING_ENABLED to true in your wrangler.toml, the worker can route requests to different Umbraco Cloud projects based on the alias.

›What is required for the multi-tenant configuration?

Each Umbraco Cloud project must register an OpenIddict client with the specific ID umbraco-cms-developer-mcp-hosted.