How to integrate Scrape do MCP with CrewAI

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

Introduction

This guide walks you through connecting Scrape do to CrewAI using the Composio tool router. By the end, you'll have a working Scrape do agent that can scrape product prices from a dynamic website, extract news headlines with javascript rendering, bypass cloudflare to get full page html, scrape mobile version of a web page through natural language commands.

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

The Scrape do MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Scrape do account. It provides structured and secure access to robust web scraping tools, so your agent can perform actions like scraping dynamic pages, managing sessions, setting custom headers or proxies, and extracting structured data from any website on your behalf.

  • Dynamic page scraping with headless browsers: Retrieve fully rendered HTML content from JavaScript-heavy or protected websites by leveraging advanced browser emulation and proxy rotation.
  • Custom scraping session management: Set device type, cookies, wait times, and custom headers to imitate different users, maintain sessions, or access device-specific content for tailored data extraction.
  • Proxy and anti-bot bypass control: Enable super or proxy modes to utilize residential, mobile, or datacenter proxies, helping your agent bypass strict anti-bot systems and geo-restrictions seamlessly.
  • Targeted resource filtering: Block specific URLs like ads or analytics scripts during scraping to increase speed, avoid distractions, and improve privacy.
  • Account usage and statistics retrieval: Access real-time usage stats, subscription status, and remaining request limits so your agent can monitor scraping quotas and avoid interruptions.

Supported Tools & Triggers

Tools
Get Account InformationRetrieves account information and usage statistics from scrape.
Get rendered page contentThis tool allows you to scrape web pages with javascript rendering enabled.
Scrape webpage using scrape.doA tool to scrape web pages using scrape.
Use Scrape.do Proxy ModeThis tool implements the proxy mode functionality of scrape.
Set Cookies for ScrapingThis tool allows users to set specific cookies for their scraping requests to a target website.
Set Scrape.do Super ModeThe scrape do set super mode tool enables enhanced scraping by using residential and mobile proxies, bypassing blocks and restrictions associated with datacenter ips.
Block specific URLs during scrapingThis tool allows users to block specific urls during the scraping process.
Set custom headers for scrape.do requestA tool to send custom headers with scrape.
Set Custom Wait TimeThis tool sets the custom wait time in milliseconds after page load when using the render option in scrape.
Set Device Type for ScrapingThis tool allows users to set the device type (desktop, mobile, or tablet) for making scraping requests.
Set Disable RedirectionControls the automatic redirection behavior of scrape.
Set Pure Cookies ModeThis tool enables getting the original set-cookie headers from target websites instead of the processed scrape.
Set Regional Geolocation for ScrapingThis tool allows users to set a broader geographical targeting by specifying a region code instead of a specific country code.
Set Retry TimeoutThis tool allows users to set the maximum wait time (in milliseconds) before retrying a failed request in scrape.
Set Screenshot Capture for ScrapingThis tool enables the screenshot functionality for the scrape.
Set Session ID for Sticky SessionsThis tool implements the session id functionality for scrape.
Set Wait For SelectorThis action allows setting a css selector to wait for before considering the page load complete.
Set Wait Until ConditionThis tool sets the waituntil parameter for the scrape.
Monitor WebSocket requests using scrape.doThis tool provides the ability to view websocket requests made by a webpage.

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 Scrape do 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 Scrape do 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 Scrape do MCP URL

Create a Composio Tool Router session for Scrape do

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

Complete Code

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

python
# file: crewai_scrape_do_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 Scrape do session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["scrape_do"],
    )
    url = session.mcp.url

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

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Scrape do MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Scrape do MCP with Claude Agent SDK

Google ADK

Google ADK

Use Scrape do MCP with Google ADK

LangChain

LangChain

Use Scrape do MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Scrape do MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Scrape do MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Scrape do MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Scrape do MCP?

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

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

Yes, absolutely. You can configure which Scrape do 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 Scrape do 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