How to Use the DatoCMS MCP in Vercel AI SDK

Q: How do I query DatoCMS content using the Vercel AI SDK?

You'll use the executegraphqlcda tool on this MCP server. Pass your GraphQL query to your agent, which invokes the tool. The Vercel AI SDK then streams the JSON response directly into your application's UI.

Q: Can I create new records in DatoCMS from my Next.js app with the Vercel AI SDK?

Yes, that's what the createcmsrecord tool is for. Your agent can take user input from your UI, format it as a new DatoCMS item, and create it. You get immediate feedback streamed back to the client.

Q: What's the best way to list all content models from DatoCMS in the Vercel AI SDK?

The listglobalmodels tool is the direct way to do this. Your agent calls it, and this MCP server returns the item types. You can use this to dynamically generate forms or UI components based on your content structure.

Q: Can my agent modify existing content?

Absolutely. The patchcmsrecord tool lets your agent update any field on an existing DatoCMS item. You can build in-context editing features right into your front-end.

Stream DatoCMS content directly into your UI with the Vercel AI SDK. Your users see results appear in real-time, no spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DatoCMS MCP to Vercel AI SDK

Create your Vinkius account to connect DatoCMS 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 DatoCMS with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Content Previews

Your agent can fetch and display DatoCMS content right inside your app. Use `get_single_record` to pull a specific article or product, and the Vercel AI SDK streams it directly into your React components. The user watches the page build itself. It works for lists, too. Your AI client can call `list_cma_records` to get a collection of posts, and you can render them one by one as they arrive. This makes your UI feel incredibly responsive, not like it's waiting on a slow API call.

Build Dynamic UIs with the Vercel AI SDK

Connect your AI-powered frontend to your headless CMS. Your agent can run complex lookups using `execute_graphql_cda` to find exactly what it needs from your DatoCMS content tree. The results are streamed back, ready to become interactive UI elements. This isn't just for reading data. You can build interfaces that let users create content. Your agent uses `create_cms_record` via the MCP connection to add new items to DatoCMS, giving you a confirmation right away. It's a full-circle content management loop, powered by your agent.

Manage Media Assets

This MCP Server also handles your media. Let your agent find and display images by calling `get_media_upload` or `list_media_uploads`. The Vercel AI SDK can even render image placeholders that fill in as the real data streams from DatoCMS. You can also build tools for content cleanup. Give your agent instructions to find and remove old assets with `wipe_media_upload`. Since the action is tied to your UI, you can build a visual dashboard for admins to approve deletions.

Setup guide

Set up DatoCMS 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 DatoCMS 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 DatoCMS 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 DatoCMS. 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 DatoCMS 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 DatoCMS MCP in Vercel AI SDK

You'll use the `execute_graphql_cda` tool on this MCP server. Pass your GraphQL query to your agent, which invokes the tool. The Vercel AI SDK then streams the JSON response directly into your application's UI.

Yes, that's what the `create_cms_record` tool is for. Your agent can take user input from your UI, format it as a new DatoCMS item, and create it. You get immediate feedback streamed back to the client.

The `list_global_models` tool is the direct way to do this. Your agent calls it, and this MCP server returns the item types. You can use this to dynamically generate forms or UI components based on your content structure.

Absolutely. The `patch_cms_record` tool lets your agent update any field on an existing DatoCMS item. You can build in-context editing features right into your front-end.

Your DatoCMS content items and media files are proxied through Vinkius's ephemeral, zero-trust environment. The server only processes the data needed for a specific tool call, like a GraphQL query or a record ID. No content is stored or logged on the MCP server itself.

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