How to integrate Iterable MCP with Pydantic AI

This guide walks you through connecting Iterable to Pydantic AI using the Composio tool router. By the end, you'll have a working Iterable agent that can summarize iterable campaign performance today, add customer to welcome journey, update user email subscription status through natural language commands. This guide will help you understand how to give your Pydantic AI agent real control over a Iterable account through Composio's Iterable MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Iterable logoIterable
Api Key

Iterable is a cross-channel marketing platform for building campaigns across email, SMS, push, and in-app channels. It helps teams personalize customer journeys and optimize engagement from one place.

116 Tools

Introduction

This guide walks you through connecting Iterable to Pydantic AI using the Composio tool router. By the end, you'll have a working Iterable agent that can summarize iterable campaign performance today, add customer to welcome journey, update user email subscription status through natural language commands.

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

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

Also integrate Iterable with

OpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenClawHermesCLIGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAI

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 Iterable
  • 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 Iterable 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 Iterable MCP server, and what's possible with it?

The Iterable MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Iterable account. It provides structured and secure access to your campaigns, users, catalogs, templates, messages, and analytics, so your agent can create campaigns, manage audiences, update catalogs, control messages, and review performance on your behalf.

  • Campaign creation and control: Have your agent create campaigns from existing templates, activate or deactivate triggered campaigns, cancel scheduled campaigns, archive campaigns, or stop campaigns already running.
  • User and audience management: Let the agent create static lists, update users in bulk, export user events, delete users, or remove a person’s data and prevent future collection.
  • Catalog and content management: Direct your agent to create catalogs, add or update catalog items, inspect catalog content and field mappings, and remove items or entire catalogs.
  • Message and template operations: Instruct your agent to review email, in-app, and embedded message templates, create reusable snippets, list message types, and cancel scheduled email, push, web push, in-app, or WhatsApp messages.
  • Campaign reporting and exports: Have your agent retrieve campaign and experiment metrics, then export campaign analytics in CSV or JSON format for further analysis.

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 Iterable
  • 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 Iterable
  • MCPServerStreamableHTTP connects to the Iterable 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 Iterable
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["iterable"],
    )
    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 Iterable 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
iterable_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[iterable_mcp],
    instructions=(
        "You are a Iterable assistant. Use Iterable tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Iterable endpoint
  • The agent uses GPT-5 to interpret user commands and perform Iterable 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 Iterable.\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
  • Iterable 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 Iterable 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 Iterable
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["iterable"],
    )
    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
    iterable_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[iterable_mcp],
        instructions=(
            "You are a Iterable assistant. Use Iterable 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 Iterable.\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 Iterable through Composio's Tool Router. With this setup, your agent can perform real Iterable 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 + Iterable 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 Iterable action and event your agent gets out of the box.

Abort Campaign

Abort a running campaign to stop all in-progress message deliveries.

Activate a triggered campaign

Activates a triggered campaign by its unique ID, allowing it to process events and send messages.

Archive Campaigns

Archives one or more campaigns.

Bulk Update Users

Bulk update user data in Iterable.

Cancel Campaign

Cancel a scheduled or recurring campaign in Iterable.

Cancel Email

Cancel a scheduled email to a specific user in Iterable.

Cancel Export

Cancel a queued or running export created with the 'Start export' endpoint.

Cancel In-App Message

Cancel a scheduled in-app message to a specific user in Iterable.

Cancel Push

Cancel a scheduled push notification to a specific user in Iterable.

Cancel Web Push

Cancel a scheduled web push notification to a specific user in Iterable.

Cancel WhatsApp

Cancel a scheduled WhatsApp message to a specific user in Iterable.

Create a new campaign

Creates a new blast or triggered campaign from an existing template.

Create a catalog

Create a catalog with the specified name in Iterable.

Create Catalog Items

Asynchronously creates or updates up to 1000 catalog items with a single request.

Create a new list

Create a new static list in Iterable.

Create snippet

Creates a new code snippet in Iterable.

Deactivate Triggered Campaign

Deactivate a triggered campaign in Iterable.

Bulk delete templates

Bulk delete one or more base templates from Iterable.

Delete a catalog

Delete a catalog by its name.

Delete a Catalog Item

Deletes the specified item from a catalog.

Delete Catalog Items

Asynchronously deletes catalog items from a specified catalog in Iterable.

Delete a list

Delete a list by its listId.

Delete Metadata Table

Asynchronously deletes a metadata table by its table name.

Delete snippet

Deletes a snippet by its ID (numeric) or name (string).

Delete User By ID

Asynchronously deletes a user by userId from Iterable.

Export data to CSV

Export campaign analytics data in CSV format from Iterable.

Export Campaign Data to JSON

Export campaign analytics data in JSON format with one entry per line.

Export User Events

Export all events for a user identified by email or userId.

Forget User

Deletes the specified user's data from the Iterable project and prevents future data collection about them.

Get campaign by ID

Retrieves a campaign by its unique ID.

Get Campaign Metrics

Retrieve performance metrics for one or more campaigns.

Get Catalog Field Mappings

Tool to retrieve field mappings (field to data type) and undefined fields for a catalog in Iterable.

Get catalog item by ID

Retrieves a specific catalog item by its ID from the specified catalog.

Get email template by ID

Get an email template by templateId.

Get Embedded Messages

Retrieves embedded messages for which the specified user is eligible, grouped by placementId.

Get Embedded Template

Retrieves an embedded message template by its unique ID.

Get Experiment Metrics

Retrieve metrics for email experiments.

Get In-App Messages

Get a user's in-app messages from Iterable.

Get in-app template by ID

Retrieves an in-app template by its unique ID.

Get List Size

Get the number of users within a list.

Get push template by ID

Retrieves a push template by its unique ID.

Get SMS template

Retrieves an SMS template by its unique ID.

Get snippet by ID or name

Retrieves a snippet by its ID (numeric) or name (string).

Get template by client template ID

Retrieves an email template by its client-defined template ID.

Get User By ID

Get a user by userId from Iterable.

Get User By ID (Path)

Get a user by userId (path parameter) from Iterable.

Get User Events

Get events for a specific user by userId.

Get User Sent Messages

Get messages sent to a user by email address or userId.

Get Web In-App Messages

Get a user's web in-app messages from Iterable.

List all campaigns

Retrieves metadata about all campaigns in a project with optional pagination.

List Catalog Items

Get the catalog items for a catalog.

List Catalogs

Tool to retrieve all catalog names from Iterable.

List Channels

Get all message channels within the Iterable project.

List export files

Get the job status and files for an export started with the 'Start export' endpoint.

List Export Jobs

Retrieve a list of recent export jobs for the current project.

List Forgotten User IDs

Get hashed user IDs of forgotten users for GDPR compliance.

List Journeys

Get a list of journeys (workflows) within your Iterable project.

List Lists

Retrieve all lists within a project.

List List Users

Get all users within a list.

List Message Types

Lists all message types within a project.

List Metadata Keys

List all keys in a metadata table.

List Metadata Tables

List available metadata tables in Iterable.

List recurring campaign child campaigns

Retrieve the child campaigns generated by a recurring campaign.

List Snippets

Get all snippets for the current project.

List all templates

Retrieves metadata about all templates in a project with optional pagination.

List User Fields

Get all user fields within a project.

List Webhooks

Get all webhooks configured within the Iterable project.

Merge Users

Merge two user profiles in Iterable.

Preview email template

Generate a fully rendered HTML preview of an email template using custom data.

Preview in-app template

Generate a fully rendered HTML preview of an in-app template using custom data.

Preview List Users

Get a random sample of up to 5000 users within a list.

Replace Catalog Item

Asynchronously creates or replaces the specified catalog item in the given catalog.

Replace Metadata Item

Asynchronously creates or replaces the metadata item associated with the specified key.

Schedule Campaign

Schedule an existing campaign to be sent at a specified time.

Send Campaign

Send an existing campaign immediately in Iterable.

Send email template proof

Send a proof of an email template to a specific user.

Send in-app notification to target

Send an in-app notification to a specific user using Iterable.

Send in-app template proof

Send a proof of an in-app template to a specific user using Iterable.

Send push to target

Send a push notification to a specific user using Iterable.

Send push template proof

Send a proof of a push template to a specific user.

Send SMS template proof

Send a proof of an SMS template to a specific user.

Send WhatsApp to target

Send a WhatsApp message to a specific user using Iterable.

Start Export

Start a data export job.

Subscribe to List

Subscribe one or more users to a specific list in Iterable.

Subscribe User By ID

Subscribes a user to the specified subscription group by their userId.

Track Embedded Click

Tracks a click event on an embedded message.

Track Embedded Received

Track that an embedded message was received on a device.

Track Embedded Session

Tracks an embedded message session and related impressions in Iterable.

Track Event

Track an event in Iterable.

Track Events in Bulk

Track multiple events in bulk in Iterable.

Track Purchase

Track a purchase event in Iterable.

Trigger Campaign

Trigger a campaign to send to one or more lists of recipients.

Trigger Journey

Trigger a journey (workflow) in Iterable for a specific user or list.

Unforget User

Unforgets a previously forgotten user in Iterable, resuming data collection.

Unsubscribe from list

Remove users from a list.

Unsubscribe User By ID

Unsubscribes a user from the specified subscription group by their userId.

Update Shopping Cart

Update a user's shopping cart items in Iterable.

Update Catalog Field Mappings

Set a catalog's field mappings (data types) in Iterable.

Update Catalog Item

Asynchronously creates or updates the specified catalog item in the given catalog.

Update email template

Update an existing email template in Iterable.

Update Embedded Template

Updates an embedded message template with the specified fields.

Update in-app template

Update an existing in-app template in Iterable.

Update push template

Updates an existing push template in Iterable.

Update SMS template

Update an existing SMS template in Iterable.

Update snippet by ID or name

Updates an existing snippet by ID (numeric) or creates/updates a snippet by name (string).

Update User

Update user data or add a user if none exists in Iterable.

Update User Email

Updates a user's email address in Iterable.

Update User Subscriptions

Updates user subscription preferences in Iterable.

Bulk Update User Subscriptions

Bulk update subscription preferences for multiple users in Iterable.

Update Webhook

Update an existing webhook configuration in Iterable.

Upsert email template

Create or update an email template in Iterable.

Upsert Embedded Template

Creates an embedded message template if it doesn't exist, or updates all embedded message templates that match the provided clientTemplateId.

Upsert in-app template

Create or update an in-app template in Iterable.

Upsert push template

Create or update a push template in Iterable.

Upsert SMS template

Create or update an SMS template in Iterable.

Verify SMS Code

Verifies an SMS verification code sent to a phone number in Iterable.

FRAMEWORKS

How to build Iterable MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Iterable MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Iterable MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Iterable MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Iterable MCP with Claude Cowork

Codex logo

Codex

Use Iterable MCP with Codex

OpenClaw logo

OpenClaw

Use Iterable MCP with OpenClaw

Hermes logo

Hermes

Use Iterable MCP with Hermes

CLI logo

CLI

Use Iterable MCP with CLI

Google ADK logo

Google ADK

Use Iterable MCP with Google ADK

LangChain logo

LangChain

Use Iterable MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Iterable MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Iterable MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Iterable MCP with LlamaIndex

CrewAI logo

CrewAI

Use Iterable MCP with CrewAI

FAQ

Frequently asked questions

With a standalone Iterable MCP server, the agents and LLMs can only access a fixed set of Iterable tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Iterable and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Pydantic AI 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 Iterable tools.

Yes, absolutely. You can configure which Iterable 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.

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 Iterable data and credentials are handled as safely as possible.

Start with Iterable.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies