How to integrate Browserless MCP with CrewAI

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

Introduction

This guide walks you through connecting Browserless to CrewAI using the Composio tool router. By the end, you'll have a working Browserless agent that can download all invoices from my dashboard, extract product details from a competitor's site, take a screenshot of my homepage after login, generate a pdf of my latest blog post through natural language commands.

This guide will help you understand how to give your CrewAI agent real control over a Browserless account through Composio's Browserless 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 Browserless connection
  • Set up CrewAI with an MCP enabled agent
  • Create a Tool Router session or standalone MCP server for Browserless
  • Build a conversational loop where your agent can execute Browserless 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 Browserless MCP server, and what's possible with it?

The Browserless MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Browserless account. It provides structured and secure access to browser automation tools, so your agent can perform actions like fetching web content, scraping data, generating PDFs, taking screenshots, and running custom browser scripts on your behalf.

  • Dynamic web content extraction: Instruct your agent to fetch full HTML content—including JavaScript-rendered pages—from any website.
  • Automated web scraping: Let your agent extract structured data from pages using CSS selectors, returning results in convenient JSON format.
  • On-demand PDF generation: Have your agent instantly generate PDFs from any webpage, with customizable parameters like format and filename.
  • Website screenshot capture: Direct your agent to take high-quality screenshots of entire pages or specific sections, supporting multiple image formats and options.
  • Custom browser automations: Empower your agent to execute tailored Puppeteer scripts, enabling powerful workflows like file downloads or bypassing bot protections.

Supported Tools & Triggers

Tools
Download file using Puppeteer scriptThis tool allows downloading files that chrome has downloaded during the execution of puppeteer code.
Execute Custom FunctionA tool that allows executing custom puppeteer scripts via http requests.
Fetch HTML ContentThis tool fetches the complete html content of a webpage using browserless's content api.
Generate PDF from webpageThis tool generates a pdf from a specified webpage using browserless's pdf generation api.
Scrape webpage content using CSS selectorsA tool to extract structured content from a webpage by specifying css selectors.
Take ScreenshotA tool that captures a screenshot of a webpage using browserless's screenshot api.
Unblock Protected ContentThis tool provides access to content from websites that implement bot protection mechanisms.

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 Browserless 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 Browserless 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 Browserless MCP URL

Create a Composio Tool Router session for Browserless

python
composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
session = composio.create(
    user_id=os.getenv("USER_ID"),
    toolkits=["browserless"],
)
url = session.mcp.url
What's happening:
  • You create a Browserless only session through Composio
  • Composio returns an MCP HTTP URL that exposes Browserless 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="Browserless Assistant",
    goal="Help users interact with Browserless through natural language commands",
    backstory=(
        "You are an expert assistant with access to Browserless tools. "
        "You can perform various Browserless 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 Browserless 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 Browserless 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 Browserless 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_browserless_agent.py

Complete Code

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

python
# file: crewai_browserless_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 Browserless session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["browserless"],
    )
    url = session.mcp.url

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

    # Create Browserless assistant agent
    toolkit_agent = Agent(
        role="Browserless Assistant",
        goal="Help users interact with Browserless through natural language commands",
        backstory=(
            "You are an expert assistant with access to Browserless tools. "
            "You can perform various Browserless 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 Browserless 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 Browserless 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 Browserless through Composio's Tool Router. The agent can perform Browserless 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 Browserless MCP Agent with another framework

OpenAI Agents SDK

OpenAI Agents SDK

Use Browserless MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Browserless MCP with Claude Agent SDK

Google ADK

Google ADK

Use Browserless MCP with Google ADK

LangChain

LangChain

Use Browserless MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Browserless MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Browserless MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Browserless MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Browserless 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 Browserless 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