io.github.umbraco/Umbraco-CMS-MCP-Dev MCP Server
io.github.umbraco/Umbraco-CMS-MCP-Dev
AI-powered Umbraco CMS content management through natural conversation and the Management API.
What is the io.github.umbraco/Umbraco-CMS-MCP-Dev MCP server?
The Umbraco MCP server is a Model Context Protocol server for Umbraco CMS that enables AI agents to perform back office tasks through the Umbraco Management API. It authenticates using Umbraco API users and respects the CMS's standard permission system, allowing secure, permission-based access to content, media, documents, and data types.
This MCP server unlocks AI-powered workflows for Umbraco CMS by providing comprehensive access to the Management API. Instead of navigating the UI, you can instruct an AI agent to handle complex, repetitive content management tasks through natural conversation. It supports both local Claude Desktop deployment and multi-tenant Umbraco Cloud hosting via Cloudflare Workers.
How to install io.github.umbraco/Umbraco-CMS-MCP-Dev
Copy-paste configuration for popular MCP clients.
UMBRACO_CLIENT_IDrequiredsecretUmbraco API user client ID
UMBRACO_CLIENT_SECRETrequiredsecretUmbraco API user client secret
UMBRACO_BASE_URLrequiredBase URL of your Umbraco instance
UMBRACO_INCLUDE_TOOL_COLLECTIONSComma-separated list of tool collections to include (e.g., document,media,document-type)
UMBRACO_READONLYEnable readonly mode to disable all write operations (create, update, delete). Only read and query tools remain available.
Tools & capabilities
Tools this server exposes to the agent.
Document management— Create, read, update, and manage Umbraco documents through the Management APIMedia management— Handle media assets and library operations via the Management APIDocument type operations— Access and manage document type definitionsData type operations— Work with Umbraco data types and property editors
Use cases
- Automate repetitive content creation and publishing workflows in Umbraco
- Query and update documents, media, and content structures via natural language commands
- Manage document types and data types without manual UI navigation
- Batch operations on content that would be tedious to perform manually
- Integrate Umbraco CMS operations into AI-assisted development workflows
io.github.umbraco/Umbraco-CMS-MCP-Dev MCP server FAQ
It's an MCP server that connects AI agents like Claude to Umbraco CMS, enabling them to perform back office tasks (document management, media handling, content updates) through the Management API using natural conversation.
Yes, the Umbraco MCP server is open-source and available on npm as @umbraco-cms/mcp-dev. You need an Umbraco CMS instance (which has free and paid tiers).
Install Claude Desktop, then add the MCP server configuration to claude_desktop_config.json with your Umbraco API credentials (client ID, secret, and base URL), and restart Claude.
You must create an Umbraco API user with appropriate permissions. The MCP server authenticates using that user's credentials and respects Umbraco's standard permission system.
Yes, it includes a Cloudflare Worker entry point supporting both single-tenant and multi-tenant Umbraco Cloud deployments via the @umbraco-cms/mcp-hosted library.
The server exposes tools for document management, media management, document type operations, and data type operations, configured via the UMBRACO_INCLUDE_TOOL_COLLECTIONS environment variable.
README (reference)
Source of truth, from the repository.
Umbraco MCP 
An MCP (Model Context Protocol) server for Umbraco CMS that unlocks AI-powered content management. It provides comprehensive access to the Umbraco Management API, enabling your AI agent to perform back office tasks through natural conversation - freeing you from the UI and making complex, repetitive workflows that would be tedious or impossible manually become effortless.
Intro
The MCP server authenticates using an Umbraco API user, ensuring secure, permission-based access to the Umbraco Management API. This means you maintain complete control over what your AI agent can do through Umbraco's standard user permission system - no special security model required.
Quick Start
1. Create an Umbraco API User
First, create an Umbraco API user with appropriate permissions. You can find instructions in Umbraco's documentation.
2. Install in Claude Desktop
Download and install the Claude Desktop app, then add the MCP server to your configuration:
- Open Claude Desktop Settings > Developer > Edit Config
- Add this configuration to your
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"
}
}
}
}
- Fully restart Claude Desktop (including in the system tray on Windows)
Documentation
For complete installation instructions, configuration options, tool listings, and usage examples, see the full documentation:
Hosted Deployment
The Cloudflare Worker entry point (src/worker.ts) supports two deployment modes, selected at request time by the @umbraco-cms/mcp-hosted library:
- Single-tenant (default) — the worker authenticates against the
UMBRACO_BASE_URLconfigured inwrangler.toml. This is the existing behavior and requires no extra configuration. - Multi-tenant Umbraco Cloud — set
UMBRACO_CLOUD_ROUTING_ENABLED = "true"under[vars]inwrangler.toml. Requests to/at/{alias}/...resolve the upstream Umbraco Cloud project for{alias}and issue access tokens scoped to that resource per the MCP resource-indicator spec. Each Umbraco Cloud project served by the worker must register an OpenIddict client with idumbraco-cms-developer-mcp-hosted.
siteRouting is wired unconditionally; the per-request toggle is the env var.
Contributing with AI Tools
This project is optimized for development with AI coding assistants. We provide instruction files for popular AI tools to help maintain consistency with our established patterns and testing standards.
Using rulesync
The project includes rulesync configuration files that can automatically generate instruction files for 19+ AI development tools. Generate configuration files for your preferred AI tools:
# Generate only for Claude Code
npx rulesync generate --claudecode
# Generate only for Cursor
npx rulesync generate --cursor
# Generate only for Vs Code Copilot
npx rulesync generate --copilot
Other AI Tools
rulesync supports 19+ AI development tools including GitHub Copilot, Cline, Aider, and more. Check the rulesync repository for the complete list of supported tools.
The instruction files cover:
- MCP development patterns and conventions
- TypeScript implementation guidelines
- Comprehensive testing standards with builders and helpers
- Project-specific context and architecture
- API integration patterns with Umbraco Management API
Related MCP servers

Persistent SQLite-backed project memory for LLMs—never re-explain your project again.

Agent Abilities for MCP
Self-hosted WordPress MCP server with per-capability permission controls and a full audit log.
One website's first-party API as MCP tools, e.g. airbnb.com. Thousands of sites indexed.

Unbrowse
Route layer for AI agents: learn website APIs from browsing, reuse them for 3.6× speedup, keep credentials local.
Read-only MCP server for Hostaway PMS — guest conversations, reservations, and listings

