How to integrate Kit MCP with CrewAI

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

Introduction

This guide walks you through connecting Kit to CrewAI using the Composio tool router. By the end, you'll have a working Kit agent that can add new subscriber to my welcome form, create a custom field for subscriber notes, delete an outdated broadcast by its id, create a tag called 'vip' for top customers through natural language commands.

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

The Kit MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Kit account. It provides structured and secure access to your subscriber lists, tags, forms, and automations, so your agent can perform actions like managing subscribers, creating tags, updating custom fields, and handling broadcasts on your behalf.

  • Subscriber management and automation: Add new subscribers to forms, remove subscribers, or update their details to keep your audience lists accurate and engaged.
  • Custom field and tag creation: Automatically create, update, or delete custom fields and tags, making it easy to segment and personalize your communications.
  • Webhook and event setup: Set up or remove webhooks so your agent can listen for subscriber or purchase events and trigger automations as needed.
  • Broadcast and campaign control: Delete obsolete broadcasts or manage your messaging campaigns directly through your agent for streamlined outreach.
  • Account insights and configuration: Retrieve detailed account information, including plan details and primary contact, to keep your integrations and automations running smoothly.

Supported Tools & Triggers

Tools
Add Subscriber to FormTool to add a subscriber to a specific form by id.
Create Custom FieldTool to create a new custom field for subscriber data.
Create TagTool to create a new tag in the account.
Create WebhookTool to create a new webhook subscription.
Delete BroadcastTool to delete a specific broadcast.
Delete Custom FieldTool to delete a specific custom field.
Delete SubscriberTool to delete (unsubscribe) a subscriber by id.
Delete TagTool to delete a tag by id.
Delete WebhookTool to delete a webhook by id.
Get AccountTool to retrieve current account information.
Get Account ColorsTool to retrieve list of colors associated with the account.
Get BroadcastTool to retrieve details of a specific broadcast by id.
Get Broadcast StatsTool to retrieve statistics for a specific broadcast by id.
Get Creator ProfileTool to retrieve the creator profile information for the account.
Get Email StatsTool to retrieve email statistics for the account.
List BroadcastsTool to retrieve a paginated list of all broadcasts.
List Custom FieldsTool to retrieve a paginated list of custom fields.
List FormsTool to list all forms.
List SegmentsTool to retrieve a paginated list of segments.
List SequencesTool to retrieve a paginated list of all sequences.
List SubscribersTool to retrieve a list of subscribers.
List Subscribers For FormTool to retrieve subscribers for a specific form by id.
List TagsTool to retrieve a list of all tags.
List Tag SubscribersTool to retrieve subscribers for a specific tag.
Tag SubscriberTool to associate a subscriber with a specific tag by id.
Tag Subscriber by EmailTool to associate a subscriber with a tag using an email address.
Update Account ColorsTool to update the list of colors for the account.
Update Custom FieldTool to update a custom field's label.
Update TagTool to update a tag's name by id.

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 Kit 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 Kit 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 Kit MCP URL

Create a Composio Tool Router session for Kit

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

Complete Code

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

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

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

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Kit MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Kit MCP with Claude Agent SDK

Google ADK

Google ADK

Use Kit MCP with Google ADK

LangChain

LangChain

Use Kit MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Kit MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Kit MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Kit MCP with LlamaIndex

FAQ

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

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

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

Yes, absolutely. You can configure which Kit 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 Kit 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