How to integrate Phantombuster MCP with CrewAI

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

Introduction

This guide walks you through connecting Phantombuster to CrewAI using the Composio tool router. By the end, you'll have a working Phantombuster agent that can download agent usage csv for last month, list all active agents in my account, get the country for this ip address, fetch deleted agents for recent audit through natural language commands.

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

The Phantombuster MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Phantombuster account. It provides structured and secure access to your web automation and data extraction tools, so your agent can perform actions like running agents, fetching reports, exporting usage data, and managing your automations on your behalf.

  • Agent management and monitoring: Instantly list, audit, or fetch details about all your Phantombuster agents and see which are active, deleted, or grouped together.
  • Data extraction and export: Have your agent export detailed usage reports or download CSVs of agent and container activity for analytics and compliance.
  • Automation workflow insight: Get visibility into branches, containers, and deployment differences—helping you track automation changes and resource usage.
  • Organization and account overview: Let your agent retrieve comprehensive organization information or check current API key associations for security and collaboration.
  • IP geolocation support: Enable your agent to look up the physical location of specific IP addresses for auditing or compliance checks.

Supported Tools & Triggers

Tools
Get All AgentsTool to fetch all agents associated with the current user or organization.
Get Deleted AgentsTool to get deleted agents for the current user or organization.
Get Branches DiffTool to get the length difference between the staging and release branch of all scripts.
Get All BranchesTool to fetch all branches associated with the current organization.
Get Containers Fetch AllTool to get all containers associated with a specified agent.
Get IP LocationTool to retrieve the country of a given or environment ip address.
Export Agent Usage CSVTool to export agent usage csv for current organization.
Export Container Usage CSVTool to export container usage csv for current organization.
Get OrganizationTool to fetch current organization details.
Get Agent GroupsTool to get agent groups and order for the current organization.
Get Organization ResourcesTool to get current organization's resources and usage.
Get Org Running ContainersTool to get the current organization's running containers.
Get Org Storage Lists Fetch AllTool to fetch all storage lists for the authenticated organization.
Get All ScriptsTool to fetch all scripts for the current user.
Unschedule All Agent LaunchesTool to unschedule all scheduled launches for agents.
Request AI CompletionTool to request a text completion from the ai module.
Create BranchTool to create a new branch.
Delete BranchTool to delete a branch by id.
Solve hCaptchaTool to solve an hcaptcha challenge.

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 Phantombuster 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 Phantombuster 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 Phantombuster MCP URL

Create a Composio Tool Router session for Phantombuster

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

Complete Code

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

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

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

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Phantombuster MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Phantombuster MCP with Claude Agent SDK

Google ADK

Google ADK

Use Phantombuster MCP with Google ADK

LangChain

LangChain

Use Phantombuster MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Phantombuster MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Phantombuster MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Phantombuster MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Phantombuster 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 Phantombuster 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