How to Use the Crafter CMS MCP in Vercel AI SDK

Q: How do I use Crafter CMS and the Vercel AI SDK to build a live blog editor?

Connect your agent to this MCP Server. Use the writestudioxml tool to generate the post's XML from user input, then publishcraftercontent to push it live. The AI SDK streams the status of each step directly into your UI components.

Q: Can I manage Crafter CMS users from a UI built with the Vercel AI SDK?

You can list them. The liststudiousers tool returns a list of all users in the studio. You can't create or modify users with this server, but you can build a UI that displays current users.

Q: What's the best way to show Crafter CMS site structure in a Next.js app using the Vercel AI SDK?

Have your agent call the getstudiotree tool. It returns a JSON object of the folder and XML hierarchy. You can then stream this data into a recursive React component to render a live, explorable tree view of your site.

Build UIs that write, publish, and manage Crafter CMS content in real-time with the 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 Crafter CMS MCP to Vercel AI SDK

Create your Vinkius account to connect Crafter CMS 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 Crafter CMS with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate and Publish Content Live

Use `write_studio_xml` to let your AI client generate new pages based on a prompt. Then trigger `publish_crafter_content` to push the changes from the studio to the live delivery engine. Your users see the content appear without a page refresh. This isn't just a backend job. Because you're using the AI SDK, the results from the MCP server stream directly into your React or Next.js components. You can build an interface that shows the publishing workflow happening step-by-step, giving users immediate feedback.

Query Your Headless CMS from the Frontend

The `search_crafter_delivery` tool lets your agent inspect content arrays directly on the delivery engine. You can build a custom search UI where the AI client finds content and streams the results straight to the user's screen. Need to check site settings? `get_site_config` and `get_site_globals` pull back the JSON for GraphQL URL limits and other structured rules. It's a direct way to build admin panels that always show the current state of your Crafter CMS environment.

Manage Site Structure with your Vercel AI SDK App

The `get_studio_tree` tool gives your agent a JSON representation of your content folders and XML structure. You can use this to build a file explorer or a sitemap visualization that updates in real-time as the data streams in. You can also check on access with `list_studio_users`. For cleanup, `wipe_studio_xml` gives you a direct, irreversible way to remove specific content nodes. Use it carefully—it's fast and final.

Setup guide

Set up Crafter CMS 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 Crafter CMS 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 Crafter CMS 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 Crafter CMS. 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 Crafter CMS 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 Crafter CMS MCP in Vercel AI SDK

Connect your agent to this MCP Server. Use the `write_studio_xml` tool to generate the post's XML from user input, then `publish_crafter_content` to push it live. The AI SDK streams the status of each step directly into your UI components.

You can list them. The `list_studio_users` tool returns a list of all users in the studio. You can't create or modify users with this server, but you can build a UI that displays current users.

Have your agent call the `get_studio_tree` tool. It returns a JSON object of the folder and XML hierarchy. You can then stream this data into a recursive React component to render a live, explorable tree view of your site.

Vinkius handles it. You get a single endpoint token for your project. All tool calls made from your Vercel AI SDK app are authenticated through that one token, so you don't need to manage individual service credentials.

The server interacts with your site's XML content, user lists, and configuration JSON. Security is handled at the platform level. Vinkius runs every request in an ephemeral, sandboxed environment, and your connection is secured by a unique access token you control.

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