How to Use the Webiny CMS MCP in Vercel AI SDK

Q: How does the Vercel AI SDK handle content publishing from Webiny CMS?

You use publishcmsentry with a specific revision ID. Your streaming client calls this tool, and the resulting confirmation streams back to your user interface immediately. It’s instant feedback for publishing drafts.

Q: Can I read specific Webiny CMS entry details using the Vercel AI SDK?

Yeah, you can. Just call getmodelentrydetails and provide the revision ID. The data streams back piece by piece, letting your client display complex nested fields as they arrive.

Q: What happens if I try to update a Webiny CMS entry using the Vercel AI SDK?

You use updatecmsentry with the ID and new field data. The agent executes this, and your streaming client immediately gets confirmation of which fields were successfully changed.

Q: Does the Webiny CMS integration support multiple model types?

Absolutely. You can use listmodelentries by providing different plural names (like 'Articles' or 'Products'). Your Vercel AI SDK client handles listing and retrieving drafts for any content model.

Q: If I run a query, what data does the Webiny CMS MCP Server provide?

It provides structured JSON results based on your executegraphqlquery. This allows your Vercel AI SDK client to process and display complex schema-driven content in real time.

Get real-time CMS data into your frontend using 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 Webiny CMS MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Content Updates with Webiny CMS

You can stream content changes directly to the UI. Use `list_model_entries` and then pipe the results into your streaming function. The user sees a draft article populating, not just an empty loading spinner. The SDK supports calling tools like `update_cms_entry` in real-time. This lets your agent update fields on the Webiny CMS record and stream the confirmation back to the frontend instantly.

Fetch CMS Metadata for Client Pages

Need global settings or schema details? Call `get_tenant_config` first. Your client can then use that foundational data to build UI components specific to Webiny CMS. Also, run `get_api_introspection` when setting up a new page view. This gives your agent the full GraphQL blueprint it needs before attempting any complex reads or writes.

Execute Direct Content Mutations

Need to push data without building a dedicated API layer? Run `execute_graphql_query` directly from the client. You specify if you're managing, reading, or previewing content in Webiny CMS. This tool gives granular control; for example, you can run a mutation via `create_cms_entry` to generate test data drafts and stream that creation confirmation right into your app.

Setup guide

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

You use `publish_cms_entry` with a specific revision ID. Your streaming client calls this tool, and the resulting confirmation streams back to your user interface immediately. It’s instant feedback for publishing drafts.

Yeah, you can. Just call `get_model_entry_details` and provide the revision ID. The data streams back piece by piece, letting your client display complex nested fields as they arrive.

You use `update_cms_entry` with the ID and new field data. The agent executes this, and your streaming client immediately gets confirmation of which fields were successfully changed.

Absolutely. You can use `list_model_entries` by providing different plural names (like 'Articles' or 'Products'). Your Vercel AI SDK client handles listing and retrieving drafts for any content model.

It provides structured JSON results based on your `execute_graphql_query`. This allows your Vercel AI SDK client to process and display complex schema-driven content in real time.

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