How to Use the Netlify MCP in Vercel AI SDK

Q: How do I connect Netlify to the Vercel AI SDK?

Install @ai-sdk/mcp and instantiate createMCPClient with your HTTP transport URL. Call mcpClient.tools() to grab the Netlify endpoints, then pass them into generateText or streamText. Always remember to call mcpClient.close() when the session ends.

Q: Can the Vercel AI SDK stream Netlify build logs?

Yes, you fetch the data using the listbuilds tool. The SDK streams the resulting JSON payload straight to your frontend, updating the UI before the entire response finishes.

Build live Netlify management dashboards in React using the Vercel AI SDK to stream build logs and site data straight to users.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Netlify MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Netlify MCP Server Data Directly to React

The `list_sites` and `get_site` tools feed live deployment statuses straight into your Vercel AI SDK frontend components. Instead of forcing users to wait for a backend polling loop to finish, you pipe the MCP Server payload right into your Next.js UI. Your users watch the page populate dynamically. Calling `list_builds` pushes the build queue history into a chat interface or dashboard widget as soon as the API responds.

Trigger and Monitor Edge Builds

The `trigger_build` tool lets your agent kick off new deployments based on chat commands or automated routines. You tie this action to a chat input, allowing a project manager to rebuild a staging environment without touching the Netlify console. Once the command executes, you immediately fetch the result using `get_deploy`. The user sees the new commit hash and build state appear instantly in their Vue or Svelte application.

Read Form Submissions Live

The `list_forms` and `list_form_submissions` tools pull recent user inputs from your static sites. Connecting these endpoints to `streamText` means your internal dashboard renders incoming contact requests in real-time. Support teams review the lead data without opening a separate browser tab. By wrapping this in your Vercel AI SDK setup, you build custom views over the raw API responses.

Setup guide

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

Install `@ai-sdk/mcp` and instantiate `createMCPClient` with your HTTP transport URL. Call `mcpClient.tools()` to grab the Netlify endpoints, then pass them into `generateText` or `streamText`. Always remember to call `mcpClient.close()` when the session ends.

Yes, you fetch the data using the `list_builds` tool. The SDK streams the resulting JSON payload straight to your frontend, updating the UI before the entire response finishes.

The HTTP transport method works perfectly in edge environments. You pass the MCP endpoint into your route handler, and it executes without needing a heavy Node.js runtime.

The API returns an error payload through the tool interface. Your React components catch this state and render a fallback message immediately.

Vinkius isolates your connection in an ephemeral V8 sandbox so no raw contact form submissions are stored. Your agent fetches the payload via `list_form_submissions` and sends it directly to your client application over a zero-trust channel.

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