How to integrate Thanks io MCP with OpenAI Agents SDK

BOOK A CALLGET STARTED FOR FREE
Framework Integration Gradient
Thanks io Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Thanks io to the OpenAI Agents SDK 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 OpenAI Agents SDK 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 and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Thanks io
  • Configure an AI agent that can use Thanks io as a tool
  • Run a live chat session where you can ask the agent to perform Thanks io operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Thanks io project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Thanks io.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Thanks io Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["thanks_io"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only thanks_io.
  • The router checks the user's Thanks io connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Thanks io.
  • This approach keeps things lightweight and lets the agent request Thanks io tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Thanks io. "
        "Help users perform Thanks io operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Thanks io and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Thanks io operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Thanks io.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Thanks io and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["thanks_io"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Thanks io. "
        "Help users perform Thanks io operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Thanks io MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Thanks io.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Thanks io MCP Agent with another framework

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

CrewAI

CrewAI

Use Thanks io MCP with CrewAI

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 OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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