SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Customerio MCP with Pydantic AI

Connect Pydantic AI to Customerio MCP. List all segments in your workspace, get delivery metrics for last week's emails, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Customerio logoCustomerio
Api Key

Customer.io is a customer engagement platform for targeted messaging across email, SMS, and push. Easily automate, segment, and track communications with your audience.

39 Tools

Introduction

This guide walks you through connecting Customerio to Pydantic AI using the Composio tool router. By the end, you'll have a working Customerio agent that can identify people, track events and page views, trigger broadcasts, review segments and metrics, and suppress or unsubscribe customers through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Customerio account through Composio's Customerio MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Customerio with

Claude CodeChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Customerio
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Customerio workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

What is the Customerio MCP server, and what's possible with it?

The Customerio MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Customer.io account. It provides structured and secure access to your customer engagement workspace, allowing your agent to send targeted communications, manage segments, retrieve messaging analytics, and automate customer data management on your behalf.

  • Targeted message analytics and tracking: Retrieve detailed lists of messages sent, including delivery metrics, to monitor campaign performance and engagement.
  • Segment discovery and membership management: Let your agent fetch all segments, get details for a specific segment, and list all customers in a segment for precise audience targeting.
  • Integration and webhook management: Have your agent list and review all integrations and webhooks in your workspace to streamline system connectivity and reporting.
  • Customer profile suppression: Direct your agent to permanently suppress (delete and block) customer profiles, ensuring compliance and data privacy.
  • Collection metadata retrieval: Retrieve up-to-date details for all collections in your workspace, keeping your AI-powered workflows and automations in sync with your data sources.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK 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

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
2

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.
3

Install dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Customerio
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

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

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Customerio
  • MCPServerStreamableHTTP connects to the Customerio MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Customerio
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["customerio"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Customerio tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
customerio_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[customerio_mcp],
    instructions=(
        "You are a Customerio assistant. Use Customerio tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Customerio endpoint
  • The agent uses GPT-5 to interpret user commands and perform Customerio operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Customerio.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Customerio API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Customerio and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Customerio
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["customerio"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    customerio_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[customerio_mcp],
        instructions=(
            "You are a Customerio assistant. Use Customerio tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Customerio.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Customerio through Composio's Tool Router. With this setup, your agent can perform real Customerio actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Customerio for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

Every Customerio action and event your agent gets out of the box.

Add Person to Group

Add a person to a Customer.

Author, Version, and Publish Email

Update and version a linked Design Studio email, then publish it.

Create Profile Alias

Create an alias to merge Customer.

Create Segment

Create an empty manual segment in Customer.

Suppress Customer Profile

Suppress a customer profile to permanently delete it and prevent re-adding with the same identifier.

Find Customers by Email

Return Customer.

Get Account Region

Return the region and Track API URL for the connected Customer.

Get Customer Attributes

Return one Customer.

Get Integrations

Retrieve a list of integrations in your workspace to discover configured integrations.

Get Messages

Tool to retrieve a list of messages sent from your workspace.

Get Newsletter Content Metrics

Retrieve engagement metrics for a Customer.

Get Newsletter Metrics

Retrieve aggregate engagement metrics for a Customer.

Get Segment Customer Count

Return the current number of profiles in a Customer.

Get Segment Details

Tool to retrieve details of a specific segment.

Get Segment Membership

Tool to retrieve people in a specific segment.

Get Segments

Tool to retrieve a list of segments in your workspace.

Get Transactional Metrics

Return aggregate engagement metrics for a transactional message template.

Get Trigger

Retrieves details about a specific API-triggered broadcast, including trigger ID, campaign ID, creation timestamp, recipient filter criteria, and personalization data.

Get Broadcast Triggers

Retrieve all API trigger instances for a specific broadcast/campaign.

Get Customer.io Workspace Webhooks

Retrieves all reporting webhook configurations from the Customer.

Identify Person

Identify a person in Customer.

List Activities

Return recent workspace activity-log entries with optional filters.

List Campaigns

Return Customer.

List Collections

Tool to list all Collections metadata.

List Customer Attributes

Return attributes and devices for up to 100 Customer.

List IP Addresses

Tool to retrieve the list of IP addresses used by Customer.

List Newsletters

Tool to list all newsletters.

List Snippets

Tool to list all snippets in your workspace.

List Transactional Contents

Return every language and content variant of a transactional template.

List Transactional Messages

Lists all transactional message templates in your Customer.

List Workspaces

List Customer.

Preview Email

Evaluate a Design Studio email against sample Liquid data without sending.

Search Customers

Search Customer.

Send Batch CDP Calls

Send multiple CDP calls (identify, track, page, screen, group, alias) in a single batch request.

Track Event

Tool to send an event associated with a person in Customer.

Track Page View

Track page views for website visitors through the Customer.

Track Screen View

Track mobile screen views in Customer.

Trigger Broadcast

Manually trigger a Customer.

Unsubscribe from Delivery

Tool to handle custom unsubscribe requests for email deliveries in Customer.

FRAMEWORKS

How to build Customerio MCP Agent with another framework

Claude Code logo

Claude Code

Use Customerio MCP with Claude Code

ChatGPT logo

ChatGPT

Use Customerio MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Customerio MCP with Claude Cowork

Antigravity logo

Antigravity

Use Customerio MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Customerio MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Customerio MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Customerio MCP with Grok Bot

Codex logo

Codex

Use Customerio MCP with Codex

OpenClaw logo

OpenClaw

Use Customerio MCP with OpenClaw

Hermes logo

Hermes

Use Customerio MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Customerio MCP with Atomic Agent

Google ADK logo

Google ADK

Use Customerio MCP with Google ADK

LangChain logo

LangChain

Use Customerio MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Customerio MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Customerio MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Customerio MCP with LlamaIndex

CrewAI logo

CrewAI

Use Customerio MCP with CrewAI

AutoGen logo

AutoGen

Use Customerio MCP with AutoGen

FAQ

Frequently asked questions

Start with Customerio.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Customerio tool your agent needs.Free to start.

Start building