How to Use the Builder.io MCP in Vercel AI SDK

Q: How do I stream Builder.io schema changes using the Vercel AI SDK?

You call mcpClient.tools() to grab the listmodels tool and pass it directly to streamText. The Vercel AI SDK streams the live schema structures straight to your frontend component, allowing dynamic UI generation without waiting for a full API response.

Q: Can the Vercel AI SDK create draft entries in Builder.io?

Yes. The Vercel AI SDK calls createcontententry to write new content blocks directly into your workspace. Because it runs on Edge Functions, the creation process is fast and streams the resulting entry ID back to your UI immediately.

Q: How does this MCP server handle Builder.io API limits with Vercel AI SDK?

The SDK monitors your traffic by invoking getapiusage inside its execution loop. This lets you display real-time usage metrics in your developer dashboard and throttle AI requests before hitting your subscription thresholds.

Q: How do I configure the transport for this connection?

Initialize the MCP connection using createMCPClient with an HTTP transport pointing to your Vinkius endpoint. Pass the tools directly into generateText and remember to call mcpClient.close() when the session ends to prevent memory leaks.

Q: What happens to my Builder.io workspace data during these runs?

Only the specific CMS payloads requested by getcontententry pass through the secure, ephemeral V8 isolate sandbox. No drafts, symbol configurations, or space metadata are stored on Vinkius servers after your execution ends.

Stream Builder.io CMS updates and model structures directly into your Next.js UI 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 Builder.io MCP to Vercel AI SDK

Create your Vinkius account to connect Builder.io 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 with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Builder.io content updates live to your UI

The `update_content_entry` tool lets your Vercel AI SDK application push visual CMS changes directly to your production site while streaming the progress live. Instead of waiting for a backend rebuild, your AI client writes the raw JSON payload and streams the status straight to the user interface. This setup bypasses slow loading spinners by hooking `get_content_entry` directly into the Edge-compatible Vercel AI SDK runtime. Your users watch their layout edits render on the screen in real-time as the server delivers the fresh payload.

Map Vercel AI SDK inputs to live CMS models

The `get_model` tool exposes the structural schema of your visual components directly to the Vercel AI SDK generation stream. Your application parses the exact fields required for a layout, preventing schema drift between your Next.js frontend and your CMS. By combining this with `list_models`, the Vercel AI SDK dynamically adapts its prompt structure to match your current Builder.io configuration on the fly. You get typed, UI-ready data without manual schema copying or hardcoded API calls.

Instant symbol deployment via Vercel AI SDK MCP Server

The `list_symbols` tool brings your reusable visual components directly into the Vercel AI SDK context window for immediate layout generation. This MCP server lets your AI client read global headers, footers, and buttons, then assemble them into new pages without writing custom CSS. When your agent finds the right symbol, it executes `create_content_entry` to draft the new page structure immediately. The entire assembly process streams to your admin dashboard without a single manual copy-paste action.

Setup guide

Set up Builder.io 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 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 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 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 MCP in Vercel AI SDK

You call `mcpClient.tools()` to grab the `list_models` tool and pass it directly to `streamText`. The Vercel AI SDK streams the live schema structures straight to your frontend component, allowing dynamic UI generation without waiting for a full API response.

Yes. The Vercel AI SDK calls `create_content_entry` to write new content blocks directly into your workspace. Because it runs on Edge Functions, the creation process is fast and streams the resulting entry ID back to your UI immediately.

The SDK monitors your traffic by invoking `get_api_usage` inside its execution loop. This lets you display real-time usage metrics in your developer dashboard and throttle AI requests before hitting your subscription thresholds.

Initialize the MCP connection using `createMCPClient` with an HTTP transport pointing to your Vinkius endpoint. Pass the tools directly into `generateText` and remember to call `mcpClient.close()` when the session ends to prevent memory leaks.

Only the specific CMS payloads requested by `get_content_entry` pass through the secure, ephemeral V8 isolate sandbox. No drafts, symbol configurations, or space metadata are stored on Vinkius servers after your execution ends.

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