How to Use the Builder.io (Visual CMS) MCP in Vercel AI SDK

Q: How do I stream Builder.io (Visual CMS) content directly into Vercel AI SDK using an MCP Server?

You install the @ai-sdk/mcp package and pass the Builder.io server endpoint to createMCPClient. From there, call mcpClient.tools() to expose functions like getcontent directly to your streamText function. This lets the model fetch and stream CMS data in a single run.

Q: Can I run Builder.io (Visual CMS) admin mutations using Vercel AI SDK?

Yes, you can execute mutations by calling the admingraphql tool with your private API key configured. The SDK passes the GraphQL payload to the MCP Server, which runs the write operations against your Builder.io models. This lets your agent create or modify schemas during a live session.

Q: How does the Builder.io (Visual CMS) MCP Server handle asset uploads in Vercel AI SDK?

The uploadasset tool accepts file paths or URLs and pushes them directly to your Builder.io media library. Your Vercel AI SDK code can trigger this tool whenever a user drops an image into the chat interface. The returned asset URL can then be piped into your layout components.

Pipe Builder.io layout data and visual assets directly into your Vercel AI SDK frontend without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Builder.io (Visual CMS) MCP to Vercel AI SDK

Create your Vinkius account to connect Builder.io (Visual 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 Builder.io (Visual CMS) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Instant visual rendering with Vercel AI SDK

The `get_html` tool pulls pre-rendered HTML from your Builder.io models directly into the Vercel AI SDK stream. This setup lets your React or Next.js frontend render visual blocks on the fly as the LLM fetches them. You do not make the user wait for a separate REST call after the text generation finishes. By coupling this tool with edge functions, your UI displays the exact layout structure instantly. The raw HTML injects straight into the stream, cutting down layout shifts and giving your users a snappy editing experience.

Direct GraphQL schema exploration

The `query_graphql` tool runs read-only GraphQL queries against your Builder.io content models right from the streaming context. Your client runs these queries to inspect available fields before generating new page layouts. This prevents schema mismatch errors when generating dynamic visual components. It works inside your edge runtime, letting the system fetch precise nested JSON structures. You get exactly the layout nodes you need without over-fetching heavy payload data.

Automated asset management via MCP Server

The `upload_asset` tool uploads images, videos, and documents directly to your Builder.io media library. Your Vercel AI SDK client handles the file transfer in the background, making assets immediately available for page layouts. Once uploaded, you can chain this with `update_content` to swap out hero images or promotional banners automatically. The entire asset pipeline executes inside your streaming block, ensuring your UI state matches your CMS media library.

Setup guide

Set up Builder.io (Visual 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 Builder.io (Visual 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 Builder.io (Visual 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 Builder.io. 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 Builder.io (Visual 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 Builder.io (Visual CMS) MCP in Vercel AI SDK

You install the `@ai-sdk/mcp` package and pass the Builder.io server endpoint to `createMCPClient`. From there, call `mcpClient.tools()` to expose functions like `get_content` directly to your `streamText` function. This lets the model fetch and stream CMS data in a single run.

Yes, you can execute mutations by calling the `admin_graphql` tool with your private API key configured. The SDK passes the GraphQL payload to the MCP Server, which runs the write operations against your Builder.io models. This lets your agent create or modify schemas during a live session.

The `upload_asset` tool accepts file paths or URLs and pushes them directly to your Builder.io media library. Your Vercel AI SDK code can trigger this tool whenever a user drops an image into the chat interface. The returned asset URL can then be piped into your layout components.

Yes, the server runs over standard HTTP/SSE transports which are fully compatible with Vercel Edge Functions. You do not need heavy node-specific libraries to fetch or update your Builder.io models. Just close the client connection using `mcpClient.close()` once your stream finishes.

Your private API keys never touch the client browser or the LLM provider. The Vinkius MCP gateway hosts the server in a secure V8 sandbox, injecting your credentials only when executing tools like `create_content` or `delete_content`. The LLM only sees the clean tool schemas, keeping your CMS write access completely private.

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