How to integrate Thanks io MCP with CrewAI

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

Introduction

This guide walks you through connecting Thanks io to CrewAI using the Composio tool router. By the end, you'll have a working Thanks io agent that can add new customer to holiday mailing list, show all available handwritten font styles, create a mailing list for event attendees, list image templates for thank you postcards through natural language commands.

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

The Thanks io MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Thanks io account. It provides structured and secure access to your direct mail platform, so your agent can perform actions like managing mailing lists, sending personalized postcards, choosing templates, and handling recipients automatically on your behalf.

  • Mailing list management: Effortlessly create, list, or delete mailing lists, and keep your recipient groups organized for targeted campaigns.
  • Recipient automation: Quickly add or remove recipients from mailing lists, ensuring your contacts are always up to date and ready for new mailings.
  • Personalized mail creation: Enable your agent to select from available handwriting styles or image templates, so every postcard, letter, or notecard feels truly unique.
  • Template selection and preview: Browse and choose from message and image templates to customize your direct mail content for any occasion.
  • Automated sending workflows: Trigger stored send actions to deliver mailings at the right moment, keeping your outreach timely and efficient.

Supported Tools & Triggers

Tools
Add Recipient to Mailing ListTool to add a new recipient to a mailing list.
Create Mailing ListTool to create a new mailing list.
Delete Mailing ListTool to delete a mailing list.
Delete Recipient from Mailing ListTool to remove a recipient from a mailing list.
Delete Sub-AccountTool to delete a specific sub-account by id.
Execute Stored SendTool to execute a previously created stored send.
List Handwriting StylesTool to retrieve available handwriting styles.
List Image TemplatesTool to retrieve a list of available image templates.
List Mailing ListsTool to list all mailing lists.
List Message TemplatesTool to list available message templates.
Buy Radius Search Mailing ListTool to buy or append a radius search mailing list based on address and radius.
Preview letter sendTool to preview a letter send as pdf.
Preview NotecardTool to preview a notecard send.
Preview PostcardTool to preview a postcard send.
Preview Windowless LetterTool to preview a windowless letter send.
List OrdersTool to list recent orders.
Search Orders by Recipient Street AddressTool to search orders by recipient street address.
Search Orders by Recipient Full NameTool to search orders by recipient full name.
Order Summary StatisticsTool to retrieve order summary statistics for a date range.
Proof PostcardTool to generate a pdf proof of a postcard's front and back.
Create Multiple RecipientsTool to create multiple recipients at once in a mailing list.
Delete Recipient by AddressTool to delete a recipient by address and postal code.
Get Recipient DetailsTool to get details for a specific recipient by id.
Search Recipients by EmailTool to search recipients by email across mailing lists.
Update RecipientTool to update existing recipient details by recipient id.
Send PostcardTool to send a customized postcard.
Stored Send NotecardTool to create a stored send for a notecard.
Stored Send PostcardTool to create a stored send for a postcard.
Stored Send Windowless LetterTool to create a stored send for a windowless letter.
Create Sub-AccountTool to create a new sub-account.
List Sub AccountsTool to list all available sub-accounts.
Get Sub Account DetailsTool to retrieve details for a specific sub-account by id.
Update Sub-AccountTool to update details for a specific sub-account.

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 Thanks io 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 Thanks io 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 Thanks io MCP URL

Create a Composio Tool Router session for Thanks io

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

Complete Code

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

python
# file: crewai_thanks_io_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 Thanks io session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["thanks_io"],
    )
    url = session.mcp.url

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

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

OpenAI Agents SDK

OpenAI Agents SDK

Use Thanks io MCP with OpenAI Agents SDK

Claude Agent SDK

Claude Agent SDK

Use Thanks io MCP with Claude Agent SDK

Google ADK

Google ADK

Use Thanks io MCP with Google ADK

LangChain

LangChain

Use Thanks io MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Thanks io MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Thanks io MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Thanks io MCP with LlamaIndex

FAQ

What are the differences in Tool Router MCP and Thanks io MCP?

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

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

Yes, absolutely. You can configure which Thanks io 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 Thanks io 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