How to Use the Webflow MCP in Vercel AI SDK

Q: How do I check for Webflow sites using Vercel AI SDK?

You call listsites on the MCP Server. This returns a list of all web properties associated with the account. The results stream back, so your frontend shows the site names appearing piece by piece.

Q: Can Vercel AI SDK update Webflow CMS items?

Yes, you use updatecollectionitem. This allows your agent to change specific fields on a record in the CMS. Since it streams results, the user sees confirmation of the update happening right away.

Q: How do I list all Webflow pages with Vercel AI SDK?

Use the listpages tool. This command gathers every page URL and title from your webflow account. The result streams in, giving you a complete inventory for your application.

Stream Webflow Data Live in Your UI with 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 Webflow MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time Webflow CMS Updates

When your user needs site data, this tool fetches it and streams the results instantly. You can use `list_collection_items` or `get_site` to pull information that appears in the UI as it loads. This real-time stream works perfectly for edge functions. Your AI client displays CMS details—like names from a collection—without needing a slow, static loading spinner.

Publishing Webflow Sites via MCP Server

Need to push changes live? The `publish_site` tool lets your agent deploy the site directly. You're not confined to the Webflow designer; you trigger production publication using simple SDK calls. It’s great for automated deployment pipelines. After updating a collection, you can immediately call `publish_site` so the live version reflects the changes right away.

Managing Site Structure and Pages

Your agent needs to know what's on the site before it acts? Use `list_pages` or `list_collections`. These tools give your client a full map of content. This lets you build complex frontends that react to Webflow’s actual structure. Check out `list_domains` if you need to manage multiple web properties for the user. It keeps all site information centralized and easily accessible.

Setup guide

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

You call `list_sites` on the MCP Server. This returns a list of all web properties associated with the account. The results stream back, so your frontend shows the site names appearing piece by piece.

Yes, you use `update_collection_item`. This allows your agent to change specific fields on a record in the CMS. Since it streams results, the user sees confirmation of the update happening right away.

It handles site and collection metadata, specifically touching `site details` and `collection items`. The agent gets read/write access to these content structures.

Use the `list_pages` tool. This command gathers every page URL and title from your webflow account. The result streams in, giving you a complete inventory for your application.

Absolutely. Your agent interacts directly with the MCP Server to manage everything from `list_pages` to `create_collection_item`. You're bypassing the designer entirely and working through code.

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