How to integrate Hunter MCP with CrewAI

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

Introduction

This guide walks you through connecting Hunter to CrewAI using the Composio tool router. By the end, you'll have a working Hunter agent that can find all public emails at acme.com, enrich company details for tesla.com, create new lead with given info, delete a lead by their id through natural language commands.

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

The Hunter MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Hunter account. It provides structured and secure access to your lead generation and enrichment tools, so your agent can perform actions like finding emails, enriching company data, managing leads, and organizing leads lists on your behalf.

  • Email discovery and search: Instantly ask your agent to find all public email addresses for a given company or domain, complete with metadata to fuel your outreach and marketing campaigns.
  • Smart lead creation and management: Let your agent add new leads, update lead details, or delete outdated entries to keep your Hunter account organized and up-to-date.
  • Company and contact enrichment: Have the agent fetch detailed company profiles or use the Email Finder to infer the best contact email for a specific person at a target company.
  • Leads list organization: Direct your agent to create, update, or remove custom leads lists—making it easy to segment prospects for personalized marketing or sales workflows.
  • Custom attribute management: Empower your agent to create or delete custom lead attributes, tailoring your CRM data fields to match your unique business needs.

Supported Tools & Triggers

Tools
Account InformationTool to retrieve information about your hunter account.
Company EnrichmentTool to get enrichment information for a company by its domain.
Create custom lead attributeTool to create a new custom lead attribute in your account.
Create LeadTool to create a new lead.
Create Leads ListTool to create a new leads list.
Delete Custom AttributeTool to delete an existing custom attribute.
Delete LeadTool to delete a lead.
Delete Leads ListTool to delete a leads list by its id.
Domain SearchTool to search all email addresses for a given domain or company.
Email FinderTool to find the most likely email address for a person at a domain or company.
Email VerifierTool to verify the deliverability of an email address.
Get Custom AttributeTool to retrieve details of a specific custom attribute.
Get LeadTool to retrieve details of a specific lead by id.
Get Leads ListTool to retrieve details of a specific leads list by id.
List Custom AttributesTool to list all custom lead attributes in your account.
List LeadsTool to list all leads saved in your account with optional filters.
List Leads ListsTool to list all leads lists in your account.
Update Custom AttributeTool to update an existing custom attribute's label.
Update LeadTool to update details of an existing lead by id.
Update Leads ListTool to update the name of a specific leads list.
Upsert LeadTool to create or update a lead by email in one call.

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 Hunter 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 Hunter 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 Hunter MCP URL

Create a Composio Tool Router session for Hunter

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

Complete Code

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

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

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

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Hunter MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Hunter MCP with Claude Agent SDK

Google ADK

Google ADK

Use Hunter MCP with Google ADK

LangChain

LangChain

Use Hunter MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Hunter MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Hunter MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Hunter MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Hunter 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 Hunter 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