How to integrate Webflow MCP with Vercel AI SDK v6

This guide walks you through connecting Webflow to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Webflow agent that can add a new blog post to your site, list all products in your store collection, get details for order #12345 through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Webflow account through Composio's Webflow MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Webflow logoWebflow
Oauth2Api Key

Webflow is a no-code website design and hosting platform for building responsive sites and online stores. It empowers users to launch, update, and manage web content with zero coding required.

51 Tools

Introduction

This guide walks you through connecting Webflow to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Webflow agent that can add a new blog post to your site, list all products in your store collection, get details for order #12345 through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Webflow account through Composio's Webflow MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Webflow with

ChatGPTOpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenCodeCursorVS CodeOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Webflow integration
  • Using Composio's Tool Router to dynamically load and access Webflow tools
  • Creating an MCP client connection using HTTP transport
  • Building an interactive CLI chat interface with conversation history management
  • Handling tool calls and results within the Vercel AI SDK framework

What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.

Key features include:

  • streamText: Core function for streaming responses with real-time tool support
  • MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
  • Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
  • OpenAI Provider: Native integration with OpenAI models

What is the Webflow MCP server, and what's possible with it?

The Webflow MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Webflow account. It provides structured and secure access to your Webflow sites, collections, and e-commerce data, so your agent can perform actions like managing content, updating inventory, handling orders, and retrieving detailed site information on your behalf.

  • Effortless content management: Ask your agent to create, update, or delete collection items—perfect for adding new blog posts, products, or dynamic content without manual entry.
  • Comprehensive site and collection insights: Retrieve up-to-date details about your Webflow sites and collections, including schema, settings, and structure, to power content-aware automations.
  • Inventory and order automation: Have your agent check inventory levels, update stock, and mark orders as fulfilled, streamlining your Webflow e-commerce operations.
  • Bulk data handling: Let your agent list all items in a collection or all collections on a site, enabling smart reporting, audits, or content migrations with a simple prompt.
  • Seamless integration with creative workflows: Enable real-time, AI-driven updates to your site content, inventory, or orders in response to team or customer needs—no coding required.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

First, install the necessary packages for your project.

What you're installing:

  • @ai-sdk/openai: Vercel AI SDK's OpenAI provider
  • @ai-sdk/mcp: MCP client for Vercel AI SDK
  • @composio/core: Composio SDK for tool integration
  • ai: Core Vercel AI SDK
  • dotenv: Environment variable management
4

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

Create a .env file in your project root.

What's needed:

  • OPENAI_API_KEY: Your OpenAI API key for GPT model access
  • COMPOSIO_API_KEY: Your Composio API key for tool access
  • COMPOSIO_USER_ID: A unique identifier for the user session
5

Import required modules and validate environment

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
What's happening:
  • We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
  • The dotenv/config import automatically loads environment variables
  • The MCP client import enables connection to Composio's tool server
6

Create Tool Router session and initialize MCP client

typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["webflow"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Webflow tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
  • This session provides access to all Webflow-related tools through the MCP protocol
7

Connect to MCP server and retrieve tools

typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
What's happening:
  • We're creating an MCP client that connects to our Composio Tool Router session via HTTP
  • The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
  • The type: "http" is important - Composio requires HTTP transport
  • tools() retrieves all available Webflow tools that the agent can use
8

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to webflow, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
What's happening:
  • We initialize an empty messages array to maintain conversation history
  • A readline interface is created to accept user input from the command line
  • Instructions are displayed to guide the user on how to interact with the agent
9

Handle user input and stream responses with real-time tool feedback

typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
What's happening:
  • We use streamText instead of generateText to stream responses in real-time
  • toolChoice: "auto" allows the model to decide when to use Webflow tools
  • stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
  • onStepFinish callback displays which tools are being used in real-time
  • We iterate through the text stream to create a typewriter effect as the agent responds
  • The complete response is added to conversation history to maintain context
  • Errors are caught and displayed with helpful retry suggestions

Complete Code

Here's the complete code to get you started with Webflow and Vercel AI SDK:

typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["webflow"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to webflow, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});

Conclusion

You've successfully built a Webflow agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.

Key features of this implementation:

  • Real-time streaming responses for a better user experience with typewriter effect
  • Live tool execution feedback showing which tools are being used as the agent works
  • Dynamic tool loading through Composio's Tool Router with secure authentication
  • Multi-step tool execution with configurable step limits (up to 10 steps)
  • Comprehensive error handling for robust agent execution
  • Conversation history maintenance for context-aware responses

You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.
TOOLS

Supported Tools

Every Webflow action and event your agent gets out of the box.

Create Asset Folder

Tool to create a new Asset Folder within a Webflow site.

Bulk Create Collection Items

Tool to create one or multiple items in a Webflow CMS Collection across multiple locales.

Create Webflow Collection

Tool to create a new collection in a Webflow site.

Create Collection Field

Tool to create a custom field in a Webflow collection.

Create Webflow Collection Item

This tool creates a new item in a specified Webflow collection.

Create Live Webflow Collection Item

Tool to create a collection item that will be immediately published to the live site.

Delete Webflow Asset

Tool to delete an Asset from Webflow.

Delete Webflow Collection

Tool to delete a collection from Webflow using its unique identifier.

Delete Collection Field

Tool to delete a custom field from a Webflow collection.

Delete Webflow Collection Item

This tool allows you to delete a specific item from a collection in Webflow.

Delete Multiple Collection Items

Tool to delete multiple items from a Webflow collection in a single request.

Delete Webflow Webhook

Tool to remove a Webhook from Webflow.

Fulfill Order

This tool allows you to mark an order as fulfilled in Webflow's e-commerce system.

Get Asset Details

Retrieves detailed information about a specific asset by its ID from a Webflow site.

Get Asset Folder Details

Tool to retrieve details about a specific Asset Folder in Webflow.

Get Collection Details

Retrieves a specific collection by its ID from a Webflow site.

Get Collection Item

This tool retrieves a specific item from a Webflow collection.

Get Component Properties

Tool to get the default property values of a component definition.

Get Custom Domains

Tool to retrieve all custom domains associated with a specific Webflow site.

Get Item Inventory

This tool retrieves the current inventory levels for a specific SKU item in a Webflow e-commerce site.

Get Live Collection Item

Retrieves details of a selected Collection live Item from Webflow.

Get Order Details

This tool retrieves detailed information about a specific order in Webflow.

Get Page Metadata

Tool to retrieve metadata for a single Webflow page by page_id.

Get Page DOM Content

Tool to retrieve the DOM/content node structure for a Webflow static page.

Get Webflow Site Information

This tool retrieves detailed information about a specific Webflow site.

Get Token Authorized By

Tool to retrieve information about the user who authorized the access token.

List Asset Folders

Tool to list all asset folders within a given Webflow site.

List Webflow Assets

Tool to retrieve all assets (images, files) uploaded to a Webflow site.

List Collection Items

This tool retrieves a list of items from a specified collection in Webflow.

List Webflow Collections

This tool retrieves a list of all collections for a given Webflow site.

List Comment Threads

Tool to list all comment threads for a Webflow site.

List Form Submissions

This tool retrieves a list of form submissions for a specific Webflow site.

List Webflow Orders

This tool retrieves a list of all orders for a specified Webflow site using the GET /sites/{site_id}/orders endpoint.

List Pages

This tool retrieves a list of all pages for a specified Webflow site.

List Webflow Sites

This tool retrieves a list of all Webflow sites accessible to the authenticated user.

List Webflow Webhooks

Tool to list all App-created Webhooks registered for a given site.

Publish Collection Items

Tool to publish one or multiple staged collection items in Webflow.

Publish Webflow Site

This tool publishes a Webflow site, making all staged changes live.

Refund Order

This tool allows you to refund a Webflow e-commerce order.

Unfulfill Order

This tool allows you to mark a previously fulfilled order as unfulfilled in Webflow.

Unpublish Live Collection Item

Tool to unpublish a live item from the Webflow site and set the isDraft property to true.

Unpublish Live Collection Items

Tool to unpublish up to 100 items from the live site and set isDraft property to true.

Update Collection Field

Tool to update a custom field in a Webflow collection.

Update Collection Item (V2 Single)

Tool to update a selected Item in a Webflow Collection using the single-item PATCH endpoint.

Update Item Inventory

This tool allows you to update the inventory levels of a specific SKU item in your Webflow e-commerce site by either setting the inventory quantity directly or updating it incrementally.

Update Live Webflow Collection Item

Tool to update a selected live Item in a Webflow Collection.

Update Live Collection Items

Tool to update single or multiple published items (up to 100) in a Webflow Collection.

Update Order

This tool allows updating specific fields of an existing order in Webflow.

Update Page Metadata

Tool to update page-level metadata in Webflow including SEO and Open Graph fields.

Update Webflow Site

Tool to update a Webflow site's properties such as name and parent folder.

Upload Asset to Webflow

This tool allows users to upload assets (files, images, etc.

FRAMEWORKS

How to build Webflow MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Webflow MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Webflow MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Webflow MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Webflow MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Webflow MCP with Claude Cowork

Codex logo

Codex

Use Webflow MCP with Codex

Cursor logo

Cursor

Use Webflow MCP with Cursor

OpenClaw logo

OpenClaw

Use Webflow MCP with OpenClaw

Hermes logo

Hermes

Use Webflow MCP with Hermes

CLI logo

CLI

Use Webflow MCP with CLI

Google ADK logo

Google ADK

Use Webflow MCP with Google ADK

LangChain logo

LangChain

Use Webflow MCP with LangChain

Mastra AI logo

Mastra AI

Use Webflow MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Webflow MCP with LlamaIndex

CrewAI logo

CrewAI

Use Webflow MCP with CrewAI

OpenCode logo

OpenCode

Use Webflow MCP with OpenCode

VS Code logo

VS Code

Use Webflow MCP with VS Code

FAQ

Frequently asked questions

With a standalone Webflow MCP server, the agents and LLMs can only access a fixed set of Webflow tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Webflow and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Webflow tools.

Yes, absolutely. You can configure which Webflow scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Webflow data and credentials are handled as safely as possible.

Start with Webflow.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Webflow tool your agent needs.Free to start.

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies