Umbraco MCP for AI. Control content, media, and drafts autonomously.

Q: What's the difference between getdeliverycontentbyid and querydeliverycontent?

getdeliverycontentbyid retrieves one item when you know its GUID. querydeliverycontent is for searching—it filters a large set of content items based on criteria like content type or author.

Q: When using listdeliverycontent, how do I fetch content beyond the first page?

You must manage pagination using the take and skip parameters. Send a request with a smaller batch size (e.g., take=50) and increment the skip value on successive calls to iterate through all available items.

Q: Before I use createcmsdocument, how do I find out what content schemas exist?

You need to run listdocumenttypes. This tool returns a complete catalog of every document type (schema) configured in Umbraco. Use this list to ensure your JSON payload matches the required structure.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Umbraco MCP Server gives your AI agent full control over Umbraco CMS content and media. You can list public pages, create drafts in the backoffice, update existing documents, or pull specific assets—all using natural conversation.

It handles everything from structured data retrieval to binary file management without you touching a GUI.

What your AI can do

Create cms document

Creates a brand new document within the Umbraco CMS using provided JSON data and adhering to defined schemas.

Delete cms document

Permanently removes an existing document from the Umbraco CMS. This action cannot be undone.

Get delivery content by id

Retrieves a specific published content item using its unique GUID or numeric ID via the Delivery API.

+ 7 more capabilities included

Fetch Content by URL Path

Retrieves a specific published piece of content using only its full web path, like /products/new-feature.

List All Available Schemas

Grabs a complete list of every Document Type (schema) defined in your Umbraco environment.

Create Backoffice Drafts

Pushes new document drafts into the CMS by providing structured data as a JSON object.

Bulk Update Content Fields

Modifies specific fields of an existing Umbraco document using its ID and updated JSON data.

Delete CMS Documents

Permanently removes a draft or published document from the Umbraco system.

Query Content by Type

Filters and lists content items using specialized query syntax, such as finding all entries with contentType:blogPost.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Umbraco MCP Server: 10 Tools for Content Management

Use these tools to manage the entire lifecycle of Umbraco content, from listing media assets to updating live drafts via API calls.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Umbraco on Vinkius

Create Cms Document

Creates a brand new document within the Umbraco CMS using provided JSON data and adhering to defined schemas.

Delete Cms Document

Permanently removes an existing document from the Umbraco CMS. This action cannot be...

Get Delivery Content By Id

Retrieves a specific published content item using its unique GUID or numeric ID via...

Get Delivery Content By Path

Fetches a specific piece of published content by knowing its exact URL path (e.g....

Get Management Document

Retrieves drafts or non-published documents directly from the Umbraco backoffice...

List Delivery Content

Lists content available through the Delivery API, supporting pagination when dealing with large datasets.

List Document Types

Provides a full list of all document types (schemas) defined and used within your Umbraco site.

List Media Assets

Lists every media asset, such as images or files, stored in the Umbraco Media...

Query Delivery Content

Filters and searches content items using advanced query syntax specific to the...

Update Cms Document

Updates fields of an existing document in Umbraco by providing its ID and a JSON...

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Umbraco integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "umbraco": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Umbraco tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"umbraco": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Umbraco, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,000+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Umbraco. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Dealing with Content APIs shouldn't mean switching between 5 different tabs.

Today, updating content is a pain. You find the item in the CMS GUI. You copy its GUID. You switch to your local IDE to grab the schema structure. Then you write boilerplate code just to make a simple PATCH request back into Umbraco. It's constant context switching and manual data plumbing.

With this MCP server, you eliminate that entire headache. Your agent handles it all in one chat window. You simply tell your agent: 'Update the title of the product at `/widgets/new` to X.' The agent calls `update_cms_document`, runs the API call, and confirms the change—all without you leaving your primary development tool.

Umbraco MCP Server: Get data, create content, manage media.

Manual processes used to require separate calls for everything: one API call just to list the types (`list_document_types`), another to fetch a specific item (`get_delivery_content_by_path`), and yet a third step just to get the media assets (`list_media_assets`). This was slow, brittle, and required complex orchestrating code.

Now, your agent coordinates all that. You can ask it: 'List all blog posts AND grab their featured image.' The agent runs `query_delivery_content` and then calls `get_delivery_content_by_id` while pulling the media details via `list_media_assets`. It delivers one complete, usable JSON object.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Listen up. This Umbraco MCP Server gives your AI agent full control over the entire CMS content and media stack. You don't gotta touch the GUI or wrestle with dashboards—your agent handles everything using natural conversation.

Here’s how you use it:

Content Retrieval & Publishing:

You can pull up specific, published content pieces by knowing their exact URL path; for instance, if someone hits /products/new-feature, your agent pulls that whole article. If you know the unique GUID or numeric ID of a live piece, it grabs that too using the Delivery API.
Want to see everything public? Your agent lists all available content through the Delivery API and handles pagination so you don't miss anything in large sites.
You can filter down massive datasets by type—say, pulling only entries where contentType:blogPost exists. This tool uses advanced query syntax specific to Umbraco’s Delivery API, letting your agent search like a pro.

Backoffice Drafting & Management:

Need to work on something that isn't ready for the public? Your agent fetches drafts or non-published documents directly from the Umbraco backoffice using the Management API. This means you can review content before it ever hits the live site.
If you gotta make a new document draft, your agent builds it for you. It creates brand new documents in the CMS by accepting structured data via JSON and making sure that payload adheres to the required schema definition.
When an existing document needs a tweak, your agent updates those fields for you. You just give it the ID and a JSON object containing only the changes you want, and it pushes them live.
Sometimes, content gotta go. Your agent permanently deletes any draft or published document in Umbraco; remember, this action is irreversible.

Schema and Asset Control:

You can check out every single Document Type (schema) used across the site by calling a list of all available schemas tool. This gives you a complete map of your content structure.
For media management, your agent lists every asset—images, PDFs, whatever—stored in the Umbraco Media library. It's like getting a full inventory count of everything attached to the CMS.

Basically, it lets your AI client perform all the standard CRUD operations right inside the engine room. You tell your agent what you need done—like 'find all product pages that reference the Q3 report' or 'create a draft for the updated privacy policy'—and it handles the back-end REST calls through both the public Delivery API and the private Management/Backoffice APIs.

No more switching between an IDE, a terminal, and the CMS dashboard. Your agent manages it all.

Built · Hosted · Managed by Vinkius Umbraco MCP Server - Manage Content & Media

Server ID 019d7618-ace4-70b2-bc2e-f80acc4319a7

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is: your AI client talks to Umbraco directly using defined API functions, skipping any manual UI steps entirely.

First, you subscribe to the Umbraco MCP server on Vinkius and inject your required Umbraco Base URL and Management Auth Token.

Second, you ask your AI client (e.g., Cursor) to perform an action—like 'list all media assets' or 'create a draft for the About page'.

The agent translates that request into specific tool calls (list_media_assets or create_cms_document), executes them against Umbraco, and returns the structured data.

What Changes When You Connect

Full Lifecycle Control: Don't just read data. Use create_cms_document to push new drafts or update_cms_document to modify existing fields without logging into the CMS GUI.

Targeted Retrieval: Forget general searches. Fetch content using its exact path (get_delivery_content_by_path) or query only by schema type (query_delivery_content).

Schema Awareness: Use list_document_types to know exactly what data structures exist before you try to populate a payload, saving hours of guesswork.

Media Asset Inventory: Need to track every image? Run list_media_assets to get an absolute list of all binary files stored in the Umbraco library.

Draft Management: Access non-published content using get_management_document, allowing your agent to work with drafts before they ever hit production.

See it in action

01 01

Need to audit all product schema types.

A Platform Engineer needs to know if a new product line requires a 'ProductVariant' type. Instead of clicking through the CMS administration, they ask their agent to run list_document_types. The agent replies with an immediate list, letting them verify the exact schema name needed for coding.

02 02

Correcting a typo on a live page.

A Digital Editor spots a title error on /about-us. They ask their agent to use get_delivery_content_by_path first, confirming the current content and ID. Then, they instruct the agent to use update_cms_document, providing only the JSON payload with the corrected text.

03 03

Building a data migration script.

A Frontend Architect needs all old blog post contents for a new site build. They ask their agent to run query_delivery_content filtered by contentType:blogPost, getting structured JSON payloads ready to map directly into the headless application.

04 04

Clean up outdated drafts.

A CMS Admin wants to delete a batch of obsolete documentation. They ask their agent to list all documents via list_delivery_content (using pagination), identify the specific GUIDs, and then run delete_cms_document on each one.

The honest tradeoffs

Trying to read content without a path.

Anti-pattern

Asking the agent simply to 'get me the product page.' This is vague and doesn't specify where in Umbraco the item lives, leading to an error or a massive list dump.

The Fix

Always use get_delivery_content_by_path and provide the full URL (e.g., /products/widget-x). If you only have the ID, run get_delivery_content_by_id instead.

Updating content without knowing the schema.

Anti-pattern

The user tries to update a field called 'productDescriptionLong' but Umbraco uses 'descriptionText'. The API rejects the payload because the key doesn't match any defined Document Type.

The Fix

First, run list_document_types to see available schemas. Then, use the correct keys when calling update_cms_document.

Assuming all content is published.

Anti-pattern

A developer tries to read a draft document using only the Delivery API endpoint. The request fails because drafts are managed by the separate backoffice system.

The Fix

Use get_management_document when you specifically need to interact with unpublished or draft versions of content.

When It Fits, When It Doesn't

You use this server if your workflow requires autonomous, stateful interactions inside Umbraco. Think: 'I need the AI agent to perform a multi-step task that involves reading data and then writing changes.' Use it when you're building an automated pipeline or prototype content flow.

Don't use this if you simply need to read static, public data for display (a simple HTTP GET call is fine). Also, don't rely on it if your process requires transactions across multiple CMS platforms—it only talks to Umbraco. If you are just listing available content types, list_document_types handles that; don't try to use it for reading the actual data.

Questions you might have

How do I get a draft document using get_management_document? +

You use this tool to retrieve drafts or non-published content that isn't visible via the standard Delivery API. You must specify the document ID and provide your management credentials.

Can I bulk create multiple documents with create_cms_document? +

Yes, you supply a list of JSON objects to the tool call. The agent processes them one by one, creating multiple new drafts or structured records in Umbraco.

What's the difference between get_delivery_content_by_id and query_delivery_content? +

get_delivery_content_by_id retrieves one item when you know its GUID. query_delivery_content is for searching—it filters a large set of content items based on criteria like content type or author.

How do I update fields using update_cms_document? +

You pass the document's ID and then provide a JSON payload. The keys in your JSON must match the actual field names defined by the schema for that document type.

When using list_delivery_content, how do I fetch content beyond the first page? +

You must manage pagination using the take and skip parameters. Send a request with a smaller batch size (e.g., take=50) and increment the skip value on successive calls to iterate through all available items.

Before I use create_cms_document, how do I find out what content schemas exist? +

You need to run list_document_types. This tool returns a complete catalog of every document type (schema) configured in Umbraco. Use this list to ensure your JSON payload matches the required structure.

What is the primary use case for list_media_assets? +

This tool pulls metadata on all binary assets—images and files—stored in the media library. It doesn't touch content; it gives you a comprehensive inventory of your media resources.

If I run delete_cms_document, is there any way to recover that data? +

No. This action permanently removes the document from the Umbraco CMS context and cannot be undone by the AI agent or through subsequent API calls. Be certain of your target ID before executing it.

Can it easily retrieve the content of a page assuming I only know its URL path? +

Absolutely. Instruct the agent to 'get_delivery_content_by_path' and supply something like '/home/about'. It traverses the Delivery API native routing map and returns perfectly all inner block grids and content variables attached.

How do I ensure the JSON payloads for `create_cms_document` are exactly what Umbraco expects? +

Use the agent to first run 'list_document_types'. It pulls down the global schema blueprints. The LLM can explicitly read the allowed field types (like rich text or media pickers) and logically construct the insertion matching it exactly.

Does it pull media details dynamically? +

Yes. Pinging 'list_media_assets' grants full insight over all stored visuals inside your Umbraco media containers, returning URL addresses alongside fundamental dimension formats so the agent can reference them anywhere.

Connect to your AI in seconds.

Create cms document

Delete cms document

Get delivery content by id

Umbraco MCP Server: 10 Tools for Content Management

Make your AI actually useful.

Create Cms Document

Delete Cms Document

Get Delivery Content By Id

Get Delivery Content By Path

Get Management Document

List Delivery Content

List Document Types

List Media Assets

Query Delivery Content

Update Cms Document

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Dealing with Content APIs shouldn't mean switching between 5 different tabs.

Umbraco MCP Server: Get data, create content, manage media.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Need to audit all product schema types.

Correcting a typo on a live page.

Building a data migration script.

Clean up outdated drafts.

The honest tradeoffs

Trying to read content without a path.

Updating content without knowing the schema.

Assuming all content is published.

When It Fits, When It Doesn't

Questions you might have