How to Use the Umbraco MCP in Vercel AI SDK

Q: How can I find out all the possible schemas with Umbraco and Vercel AI SDK?

Just run listdocumenttypes. This function shows every single content type (schema) defined in your Umbraco setup. It gives your agent a complete map of what kind of data it can interact with.

Q: When I query Umbraco using the Vercel AI SDK, how do I filter by content type?

You use querydeliverycontent. You pass in a specific filter, like contentType:blogPost, and the MCP Server returns only records matching that criteria. This is much faster than listing everything.

Q: Does Umbraco support multi-step content creation with Vercel AI SDK?

Yeah. You can create a document using createcmsdocument and then immediately update it or list its assets afterward, all through the streaming interface. The whole sequence feels real-time to the end user.

Q: If I need draft content from Umbraco with Vercel AI SDK, which tool do I use?

The getmanagementdocument tool handles this. It accesses Umbraco's dedicated Management API, bypassing the published delivery layer so your agent sees unpublished drafts.

Get real-time Umbraco content updates directly into your UI with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Umbraco MCP to Vercel AI SDK

Create your Vinkius account to connect Umbraco to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Umbraco with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Document Interaction via MCP Server

Need to check what's live? Use `get_delivery_content_by_path` to pull content just by its URL path, making your AI client instantly aware of the data. It fetches specific items from Umbraco’s Delivery API. Want to build a custom CMS feature? Your agent uses `create_cms_document` to generate new content records based on JSON schemas you provide, and then streams that result right into your React or Next.js components.

Managing Content Types for Vercel AI SDK

To know what data is available, call `list_document_types`. This tells your agent exactly which content schemas Umbraco supports. You can then use that knowledge with `query_delivery_content` to filter items—say, finding all 'blogPost' types without needing a specific ID. Tracking media? The `list_media_assets` tool pulls names and paths for files in the Umbraco Media library. This lets your AI client handle image links or file uploads directly within the user flow.

Updating Content on Demand with MCP Server

A piece of content needs fixing? Your agent uses `update_cms_document` to change fields on an existing document, requiring just the ID and the new data payload. It's a direct backoffice write that your client can execute as part of a user action. Don't forget reading drafts. The `get_management_document` tool lets you access content through Umbraco's management API (the back-end stuff), giving your AI client visibility into unpublished or draft versions.

Setup guide

Set up Umbraco MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Umbraco tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Umbraco transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Umbraco now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Umbraco MCP in Vercel AI SDK

Just run `list_document_types`. This function shows every single content type (schema) defined in your Umbraco setup. It gives your agent a complete map of what kind of data it can interact with.

You use `query_delivery_content`. You pass in a specific filter, like `contentType:blogPost`, and the MCP Server returns only records matching that criteria. This is much faster than listing everything.

Yeah. You can create a document using `create_cms_document` and then immediately update it or list its assets afterward, all through the streaming interface. The whole sequence feels real-time to the end user.

The `get_management_document` tool handles this. It accesses Umbraco's dedicated Management API, bypassing the published delivery layer so your agent sees unpublished drafts.

Since this MCP Server touches content schemas and media assets, you need to ensure the user token only grants read/write permissions for the specific document IDs or paths required. Never give full admin access.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript