How to integrate V0 MCP with Vercel AI SDK v6

This guide walks you through connecting V0 to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working V0 agent that can generate react code for a login page, list all your active v0 projects, summarize our last five chat sessions through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a V0 account through Composio's V0 MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

V0 logoV0
Api Key

V0 is an AI-powered web development assistant from Vercel that generates real, production-ready code for modern apps. Build modern web experiences faster with automated, intelligent code suggestions and UI components.

44 Tools

Introduction

This guide walks you through connecting V0 to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working V0 agent that can generate react code for a login page, list all your active v0 projects, summarize our last five chat sessions through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a V0 account through Composio's V0 MCP server.

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

Also integrate V0 with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with V0 integration
  • Using Composio's Tool Router to dynamically load and access V0 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 V0 MCP server, and what's possible with it?

The V0 MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your V0 account. It provides structured and secure access to your V0 projects and chat-powered workflows, so your agent can perform actions like generating code, managing web projects, retrieving chat histories, and facilitating AI-driven conversations on your behalf.

  • AI-powered chat completions: Instantly generate conversational replies or code suggestions using V0's advanced chat models tailored for web development workflows.
  • Retrieve and manage chat sessions: List and access your previous AI-assisted chat threads, including support for filtering favorites and paginated results.
  • Project discovery and management: Fetch a complete list of your web development projects, making it easy for your agent to interact with or summarize project data.
  • Integrated development automation: Seamlessly combine chat capabilities and project management to automate code generation, troubleshooting, or project setup tasks.

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: ["v0"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to V0 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 V0-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 V0 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 v0, 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 V0 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 V0 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: ["v0"],
  });

  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 v0, 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 V0 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 V0 action and event your agent gets out of the box.

Assign Chat To Project

Tool to assign a chat to a project.

V0 Chat Completions

Tool to generate a chat model response given a list of messages.

Create Webhook

Tool to create a new webhook subscription for receiving event notifications.

Create V0 Project

Tool to create a new v0 project container for chats and code generation.

Create Project Environment Variables

Tool to create new environment variables for a v0 project.

Create Vercel Project

Tool to link a Vercel project to an existing v0 project.

Delete Chat

Tool to permanently delete a specific chat by ID.

Delete Deployment

Tool to delete a deployment by ID from Vercel.

Delete Hook

Tool to delete a webhook by its ID.

Delete Project Environment Variables

Tool to delete multiple environment variables from a project by their IDs.

Delete V0 Project

Tool to permanently delete a v0 project by its ID.

Deploy Project

Tool to deploy a specific v0 chat version to Vercel.

Download Chat Version

Tool to download all files for a specific chat version as a zip or tarball archive.

Export Project Code

Tool to export a deployable snapshot of a v0 chat version by retrieving all files (including default/deployment files).

Favorite Chat

Tool to mark a chat as favorite or remove the favorite status.

Find Chats

Tool to retrieve a list of chats.

Find Projects

Tool to retrieve a list of projects associated with the authenticated user.

Find Vercel Projects

Tool to retrieve a list of Vercel projects linked to the user's v0 workspace.

Fork Chat

Tool to create a fork (copy) of an existing chat.

Get Chat

Tool to retrieve the full details of a specific chat using its chatId.

Get Chat Project

Tool to retrieve the v0 project associated with a given chat.

Get Deployment Errors

Tool to retrieve errors for a specific deployment.

Get Deployment Logs

Tool to retrieve logs for a specific deployment.

Get Hook

Tool to retrieve detailed information about a specific webhook by its ID.

Get Chat Message

Tool to retrieve detailed information about a specific message within a chat.

Get Project by ID

Tool to retrieve the details of a specific v0 project by its ID, including associated chats and metadata.

Get Project Environment Variable

Tool to retrieve a specific environment variable for a given project by its ID, including its value.

Get Rate Limits

Tool to retrieve the current rate limits for the authenticated user.

Get Usage Report

Tool to retrieve detailed usage events including costs, models used, and metadata.

Get User

Tool to retrieve the currently authenticated user's information.

Get User Billing

Tool to fetch billing usage and quota information for the authenticated user.

Get User Plan

Tool to retrieve the authenticated user's subscription plan details including billing cycle and balance.

Get User Scopes

Tool to retrieve all accessible scopes for the authenticated user, such as personal workspaces or shared teams.

Initialize Chat

Tool to initialize a new chat from source content such as files, repositories, registries, zip archives, or templates.

List Chat Versions

Tool to retrieve all versions (iterations) for a specific chat, ordered by creation date (newest first).

List Deployments

Tool to retrieve a list of deployments for a given project, chat, and version.

List Hooks

Tool to retrieve all webhooks tied to chat events or deployments.

List Messages

Tool to retrieve all messages within a specific chat.

List Project Environment Variables

Tool to retrieve all environment variables for a project with optional decryption.

Update Chat

Tool to update metadata of an existing v0 chat.

Update Chat Version Files

Tool to update source files of a specific chat version.

Update V0 Webhook

Tool to update the configuration of an existing webhook, including its name, event subscriptions, or target URL.

Update V0 Project

Tool to update the metadata of an existing v0 project using its projectId.

Update Project Environment Variables

Tool to update environment variables for a v0 project.

FAQ

Frequently asked questions

With a standalone V0 MCP server, the agents and LLMs can only access a fixed set of V0 tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from V0 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 V0 tools.

Yes, absolutely. You can configure which V0 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 V0 data and credentials are handled as safely as possible.

Start with V0.It takes 30 seconds.

Managed auth, hosted MCP servers, and every V0 tool your agent needs.Free to start.

Start building