How to integrate Reply MCP with CrewAI

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

Introduction

This guide walks you through connecting Reply to CrewAI using the Composio tool router. By the end, you'll have a working Reply agent that can list all active email campaigns this week, get contacts in my 'leads q3' list, show all available email templates, retrieve blacklisted domains and emails through natural language commands.

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

The Reply MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Reply.io account. It provides structured and secure access to your sales engagement platform, so your agent can create and manage lists, fetch campaign schedules, organize contacts, and monitor outreach performance for you.

  • Personal list creation and management: Easily instruct your agent to create, organize, or delete personal contact lists to streamline your outreach workflow.
  • Contact organization and retrieval: Have your agent fetch contacts within specific lists, helping you target and personalize campaigns more effectively.
  • Campaign and schedule insights: Ask your agent to retrieve all campaign schedules or see which campaigns a specific contact belongs to, giving you up-to-date visibility into your outreach pipeline.
  • Email account and template discovery: Let your agent pull a list of available email accounts or fetch your personal, team, and community templates for quick access while composing new campaigns.
  • Blacklist monitoring and management: Direct your agent to retrieve the full list of blacklisted domains and emails, so you can ensure compliance and maintain deliverability standards with ease.

Supported Tools & Triggers

Tools
Create Personal ListTool to add a new personal list on the people page.
Delete List By IDTool to delete a list by its id.
Get All ListsTool to retrieve all available people lists.
Get full blacklist of domains and emailsTool to retrieve the full list of blacklisted domains and emails.
Get all campaign schedulesTool to list all campaign schedules (default and user-created).
Get Campaigns For ContactTool to retrieve campaigns a contact belongs to by contact id.
Get Contacts in List by IDTool to retrieve contacts in a specific personal list.
Get Email AccountsTool to retrieve list of all email accounts in your reply.
Get List by IDTool to return a specific people list by its id.
Get templates listTool to retrieve a list of user, team, and community templates.
Mark Contact As FinishedTool to mark a specific contact by email or all contacts under a domain as finished in all campaigns.
Mark Contact as RepliedTool to mark a contact as replied in all campaigns by email or domain.
Move Contacts to ListsTool to move one or more contacts to specified lists.
Remove Domain from BlacklistTool to remove the specified domain from the blacklist.
Remove Email from BlacklistTool to remove the specified email from the blacklist.

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 Reply 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 Reply 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 Reply MCP URL

Create a Composio Tool Router session for Reply

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

Complete Code

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

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

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

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Reply MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Reply MCP with Claude Agent SDK

Google ADK

Google ADK

Use Reply MCP with Google ADK

LangChain

LangChain

Use Reply MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Reply MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Reply MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Reply MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Reply 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 Reply 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