SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Hyperbrowser MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Hyperbrowser MCP. Start a browser session with stealth mode, extract all product titles from this url, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Hyperbrowser logoHyperbrowser
Api Key

Hyperbrowser is a next-generation platform for scalable browser automation. It empowers AI agents to interact with web apps, automate workflows, and handle browser sessions at scale.

42 Tools

Introduction

This guide walks you through connecting Hyperbrowser to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Hyperbrowser agent that can scrape and crawl websites, extract structured data, run browser sessions, launch computer use agents, and search the web through natural language commands.

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

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

Also integrate Hyperbrowser with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Hyperbrowser MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Hyperbrowser account. It provides structured and secure access to automated browser sessions, web scraping, and browser-based task management, so your agent can launch sessions, extract data, manage automation jobs, and monitor progress on your behalf.

  • Automated browser session creation: Let your agent spin up new browser sessions with custom privacy, stealth, and proxy settings for tailored automation tasks.
  • Scalable web scraping and extraction: Easily initiate and manage scrape jobs to extract structured content from any target website, with support for session and scrape customization.
  • Real-time job status monitoring: Have your agent check, track, and report the live status of browser-use, crawl, or data extraction jobs, ensuring you always know what's happening.
  • Retrieve results from automation jobs: Fetch and review the outputs of completed crawl or extract jobs, including paginated data and detailed results, right inside your workflow.
  • Profile and automation management: Create or delete Hyperbrowser profiles as needed, giving you flexible control over your automation environment and resources.

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: ["hyperbrowser"],
  });

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

  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 hyperbrowser, 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 Hyperbrowser 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 Hyperbrowser action and event your agent gets out of the box.

Add Extension

Tool to add a new browser extension to Hyperbrowser for use in sessions.

Create Hyperbrowser Profile

Creates a new persistent Hyperbrowser profile for storing browser state (cookies, sessions, etc.

Create Scrape Job

Tool to initiate a new scrape job.

Create Session

Tool to create a new browser session with custom stealth, proxy, and privacy settings.

Delete Profile

Tool to delete a profile.

Fetch Web Page

Tool to fetch a web page and return content in various formats (HTML, Markdown, JSON, screenshot, etc.

Get browser-use task status

Tool to retrieve the current status of a browser-use task.

Get Claude Computer Use Task Result

Tool to retrieve the complete result and status of a Claude Computer Use task.

Get Claude Computer Use Task Status

Poll the execution status of a Claude Computer Use task.

Get Crawl Job Status

Tool to retrieve the status and results of a specific crawl job.

Get Crawl Status

Tool to retrieve the current status of a specific crawl job.

Get CUA Task Result

Tool to retrieve the status and results of a CUA (Claude User Agent) task.

Get CUA Task Status

Poll the execution status of a CUA task.

Get Extract Job Result

Tool to fetch the status and results of a specific extract job.

Get Extract Job Status

Retrieve the status of an extract job.

Get Gemini Computer Use task result

Tool to retrieve the current status and results of a Gemini Computer Use task.

Get HyperAgent Task Result

Tool to retrieve the status and results of a HyperAgent task.

Get Profile By ID

Retrieves details of a specific Hyperbrowser profile by its UUID.

Get Scrape Job Result

Retrieves the status and results of a scrape job.

Get Scrape Job Status

Retrieve the current status of a specific scrape job.

Get Session Details

Retrieve details of a Hyperbrowser session by ID, including status and configuration.

Get Session Downloads URL

Tool to retrieve the downloads URL for a session.

Get Session Recording

Retrieve a browser session's rrweb recording status and, when available, a pre-signed download URL.

Get Session Video Recording URL

Retrieve a browser session's video recording status and, when available, a pre-signed download URL.

Get Web Crawl Result

Tool to retrieve the status and results of a web crawl job.

Get Web Crawl Status

Tool to retrieve just the status of a web crawl job without the full results.

List Extensions

List browser extensions for the Hyperbrowser account, returning the available page and pagination metadata.

List Profiles

Tool to list profiles.

List Sessions

Tool to list sessions with optional status filter.

Search Web

Tool to perform a web search and retrieve results with titles, URLs, and descriptions.

Start Browser Use Task

Tool to start an asynchronous browser-use task.

Start Claude Computer Use Task

Tool to start a Claude Computer Use task.

Start Crawl Job

Tool to start a new crawl job for a specified URL.

Start CUA Task

Tool to start an OpenAI CUA (Computer-Using Agent) task.

Start Extract Job

Start an AI-powered data extraction job from one or more web pages.

Start Gemini Computer Use Task

Tool to start a Gemini Computer Use task for browser automation using Google's Gemini.

Start Web Crawl

Start an asynchronous web crawl job from a starting URL, with options to follow links and configure content extraction.

Stop Browser Use Task

Tool to stop a running browser-use task.

Stop Claude Computer Use Task

Tool to stop a running Claude computer use task.

Stop CUA Task

Tool to stop a running CUA task.

Stop Gemini Computer Use Task

Tool to stop a running Gemini computer use task.

Stop Session

Tool to stop a running session by ID.

FRAMEWORKS

How to build Hyperbrowser MCP Agent with another framework

Claude Code logo

Claude Code

Use Hyperbrowser MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Hyperbrowser MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Hyperbrowser MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Hyperbrowser MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Hyperbrowser MCP with Grok Bot

Codex logo

Codex

Use Hyperbrowser MCP with Codex

OpenClaw logo

OpenClaw

Use Hyperbrowser MCP with OpenClaw

Hermes logo

Hermes

Use Hyperbrowser MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Hyperbrowser MCP with Atomic Agent

Google ADK logo

Google ADK

Use Hyperbrowser MCP with Google ADK

LangChain logo

LangChain

Use Hyperbrowser MCP with LangChain

Mastra AI logo

Mastra AI

Use Hyperbrowser MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Hyperbrowser MCP with LlamaIndex

CrewAI logo

CrewAI

Use Hyperbrowser MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Hyperbrowser MCP with Pydantic AI

AutoGen logo

AutoGen

Use Hyperbrowser MCP with AutoGen

FAQ

Frequently asked questions

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

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

Start with Hyperbrowser.It takes 30 seconds.

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

Start building