How to integrate Hyperbrowser MCP with CrewAI

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Hyperbrowser Logo
CrewAI Logo
divider

Introduction

This guide walks you through connecting Hyperbrowser to CrewAI using the Composio tool router. By the end, you'll have a working Hyperbrowser agent that can start a browser session with stealth mode, extract all product titles from this url, check status of my ongoing scrape job, delete an unused hyperbrowser profile through natural language commands.

This guide will help you understand how to give your CrewAI 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.

TL;DR

Here's what you'll learn:
  • Get a Composio API key and configure your Hyperbrowser connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Hyperbrowser
  • Build a conversational loop where your agent can execute Hyperbrowser operations

What is CrewAI?

CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews.

Key features include:

  • Agent Roles: Define specialized agents with specific goals and backstories
  • Task Management: Create tasks with clear descriptions and expected outputs
  • Crew Orchestration: Combine agents and tasks into collaborative workflows
  • MCP Integration: Connect to external tools through Model Context Protocol

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.

Supported Tools & Triggers

Tools
Create Hyperbrowser ProfileTool to create a new profile.
Create Scrape JobTool to initiate a new scrape job.
Create SessionTool to create a new browser session with custom stealth, proxy, and privacy settings.
Delete ProfileTool to delete a profile.
Get browser-use task statusTool to retrieve the current status of a browser-use task.
Get Claude Computer Use Task StatusTool to retrieve the status of a Claude Computer Use task.
Get Crawl Job ResultTool to retrieve the result of a completed crawl job.
Get Crawl Job StatusTool to retrieve the status and results of a specific crawl job.
Get Extract Job ResultTool to fetch the status and results of a specific extract job.
Get Extract Job StatusTool to retrieve the status of an extract job.
Get Profile By IDTool to retrieve profile details by ID.
Get Scrape Job ResultTool to fetch the status and results of a specific scrape job.
Get Scrape Job StatusTool to retrieve the current status of a specific scrape job.
Get Session DetailsTool to retrieve session details by ID.
Get Session Downloads URLTool to retrieve the downloads URL for a session.
Get Session RecordingTool to retrieve the recording URL of a session.
List ProfilesTool to list profiles.
List SessionsTool to list sessions with optional status filter.
Start Browser Use TaskTool to start an asynchronous browser-use task.
Start Claude Computer Use TaskTool to start a Claude Computer Use task.
Start Crawl JobTool to start a new crawl job for a specified URL.
Start Extract JobTool to start an extract job.
Stop Browser Use TaskTool to stop a running browser-use task.
Stop Claude Computer Use TaskTool to stop a running Claude computer use task.
Stop SessionTool to stop a running session by ID.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account and API key
  • A Hyperbrowser connection authorized in Composio
  • An OpenAI API key for the CrewAI LLM
  • Basic familiarity with Python

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.

Install dependencies

bash
pip install composio crewai crewai-tools python-dotenv
What's happening:
  • composio connects your agent to Hyperbrowser via MCP
  • crewai provides Agent, Task, Crew, and LLM primitives
  • crewai-tools includes MCP helpers
  • python-dotenv loads environment variables from .env

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key_here

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates with Composio
  • USER_ID scopes the session to your account
  • OPENAI_API_KEY lets CrewAI use your chosen OpenAI model

Import dependencies

python
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional import if you plan to adapt tools
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()
What's happening:
  • CrewAI classes define agents and tasks, and run the workflow
  • MCPServerHTTP connects the agent to an MCP endpoint
  • Composio will give you a short lived Hyperbrowser MCP URL

Create a Composio Tool Router session for Hyperbrowser

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["hyperbrowser"],
)
url = session.mcp.url
What's happening:
  • You create a Hyperbrowser only session through Composio
  • Composio returns an MCP HTTP URL that exposes Hyperbrowser tools

Configure the LLM

python
llm = LLM(
    model="gpt-5-mini",
    api_key=os.getenv("OPENAI_API_KEY"),
)
What's happening:
  • CrewAI will call this LLM for planning and responses
  • You can swap in a different model if needed

Attach the MCP server and create the agent

python
toolkit_agent = Agent(
    role="Hyperbrowser Assistant",
    goal="Help users interact with Hyperbrowser through natural language commands",
    backstory=(
        "You are an expert assistant with access to Hyperbrowser tools. "
        "You can perform various Hyperbrowser operations on behalf of the user."
    ),
    mcps=[
        MCPServerHTTP(
            url=url,
            streamable=True,
            cache_tools_list=True,
            headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
        ),
    ],
    llm=llm,
    verbose=True,
    max_iter=10,
)
What's happening:
  • MCPServerHTTP connects the agent to the Hyperbrowser MCP endpoint
  • cache_tools_list saves a tools catalog for faster subsequent runs
  • verbose helps you see what the agent is doing

Add a REPL loop with Task and Crew

python
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to perform Hyperbrowser operations.\n")

conversation_context = ""

while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    conversation_context += f"\nUser: {user_input}\n"
    print("\nAgent is thinking...\n")

    task = Task(
        description=(
            f"Based on the conversation history:\n{conversation_context}\n\n"
            f"Current user request: {user_input}\n\n"
            f"Please help the user with their Hyperbrowser related request."
        ),
        expected_output="A helpful response addressing the user's request",
        agent=toolkit_agent,
    )

    crew = Crew(
        agents=[toolkit_agent],
        tasks=[task],
        verbose=False,
    )

    result = crew.kickoff()
    response = str(result)

    conversation_context += f"Agent: {response}\n"
    print(f"Agent: {response}\n")
What's happening:
  • You build a simple chat loop and keep a running context
  • Each user turn becomes a Task handled by the same agent
  • Crew executes the task and returns a response

Run the application

python
if __name__ == "__main__":
    main()
What's happening:
  • Standard Python entry point so you can run python crewai_hyperbrowser_agent.py

Complete Code

Here's the complete code to get you started with Hyperbrowser and CrewAI:

python
# file: crewai_hyperbrowser_agent.py
from crewai import Agent, Task, Crew, LLM
from crewai_tools import MCPServerAdapter  # optional
from composio import Composio
from dotenv import load_dotenv
import os
from crewai.mcp import MCPServerHTTP

load_dotenv()

def main():
    # Initialize Composio and create a Hyperbrowser session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["hyperbrowser"],
    )
    url = session.mcp.url

    # Configure LLM
    llm = LLM(
        model="gpt-5-mini",
        api_key=os.getenv("OPENAI_API_KEY"),
    )

    # Create Hyperbrowser assistant agent
    toolkit_agent = Agent(
        role="Hyperbrowser Assistant",
        goal="Help users interact with Hyperbrowser through natural language commands",
        backstory=(
            "You are an expert assistant with access to Hyperbrowser tools. "
            "You can perform various Hyperbrowser operations on behalf of the user."
        ),
        mcps=[
            MCPServerHTTP(
                url=url,
                streamable=True,
                cache_tools_list=True,
                headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")},
            ),
        ],
        llm=llm,
        verbose=True,
        max_iter=10,
    )

    print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
    print("Try asking the agent to perform Hyperbrowser operations.\n")

    conversation_context = ""

    while True:
        user_input = input("You: ").strip()

        if user_input.lower() in ["exit", "quit", "bye"]:
            print("\nGoodbye!")
            break

        if not user_input:
            continue

        conversation_context += f"\nUser: {user_input}\n"
        print("\nAgent is thinking...\n")

        task = Task(
            description=(
                f"Based on the conversation history:\n{conversation_context}\n\n"
                f"Current user request: {user_input}\n\n"
                f"Please help the user with their Hyperbrowser related request."
            ),
            expected_output="A helpful response addressing the user's request",
            agent=toolkit_agent,
        )

        crew = Crew(
            agents=[toolkit_agent],
            tasks=[task],
            verbose=False,
        )

        result = crew.kickoff()
        response = str(result)

        conversation_context += f"Agent: {response}\n"
        print(f"Agent: {response}\n")

if __name__ == "__main__":
    main()

Conclusion

You now have a CrewAI agent connected to Hyperbrowser through Composio's Tool Router. The agent can perform Hyperbrowser operations through natural language commands. Next steps:
  • Add role-specific instructions to customize agent behavior
  • Plug in more toolkits for multi-app workflows
  • Chain tasks for complex multi-step operations

How to build Hyperbrowser MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Hyperbrowser MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Hyperbrowser MCP with Claude Agent SDK

Google ADK

Google ADK

Use Hyperbrowser MCP with Google ADK

LangChain

LangChain

Use Hyperbrowser MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Hyperbrowser MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Hyperbrowser MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Hyperbrowser MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Hyperbrowser MCP?

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.

Can I use Tool Router MCP with CrewAI?

Yes, you can. CrewAI 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.

Can I manage the permissions and scopes for Hyperbrowser while using Tool Router?

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.

How safe is my data with Composio Tool Router?

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.

Used by agents from

Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
ASU
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free