How to integrate Postmark MCP with Pydantic AI

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Postmark logo
Pydantic AI logo
divider

Introduction

This guide walks you through connecting Postmark to Pydantic AI using the Composio tool router. By the end, you'll have a working Postmark agent that can send a password reset email to user, get delivery status for last 10 emails, list all bounced emails from today through natural language commands.

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

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

Also integrate Postmark with

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

The Postmark MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Postmark account. It provides structured and secure access to transactional email sending and analytics, so your agent can perform actions like delivering transactional emails, monitoring delivery status, managing templates, and analyzing engagement metrics on your behalf.

  • Automated transactional email delivery: Let your agent send password resets, confirmations, and notification emails with high deliverability and reliability.
  • Template management and customization: Enable your agent to create, update, or select dynamic email templates for consistent, branded communications.
  • Email delivery status monitoring: Ask your agent to track sent messages, check delivery receipts, and identify bounced or failed emails in real time.
  • Engagement and analytics tracking: Have your agent retrieve open and click data, analyze engagement trends, and provide actionable insights from your email campaigns.
  • Suppression list and recipient management: Direct your agent to manage suppression lists, process unsubscribes, and maintain healthy recipient lists automatically.

Supported Tools & Triggers

Tools
Archive Message StreamTool to archive a message stream (soft delete).
Check Spam ScoreTool to assess the spam score of a raw email via the SpamCheck API.
Create Inbound RuleTool to create a new inbound rule trigger to block email from a specific sender or domain.
Create Message StreamTool to create a new message stream.
Create SuppressionsTool to add email addresses to the suppression list for a message stream.
Create TemplateTool to create a new email template.
Create WebhookTool to create a new webhook configuration for Postmark.
Delete Inbound RuleTool to delete a specific inbound rule trigger.
Delete SuppressionsTool to remove email addresses from the suppression list for a message stream.
Delete TemplateTool to delete a template by its ID or alias.
Delete WebhookTool to delete a specific webhook.
Edit ServerTool to update settings for the current Postmark server.
Edit TemplateTool to update an existing Postmark template by its ID.
Edit WebhookTool to update an existing webhook’s URL or triggers.
Get Bounce CountsTool to get total counts of emails that have been returned as bounced.
Get BouncesTool to retrieve a list of bounces for a server with optional filters.
Get Browser Platform UsageTool to retrieve browser platform usage statistics for clicked links.
Get Browser UsageTool to retrieve browser usage statistics for clicked links.
Get Click CountsTool to retrieve total click counts across all links in emails.
Get Clicks By Browser FamilyTool to retrieve click statistics grouped by browser family.
Get Clicks by LocationTool to get an overview of which part of the email links were clicked from (HTML or Text).
Get Delivery StatsTool to retrieve delivery statistics.
Get Email Client UsageTool to retrieve statistics on email clients used to open emails.
Get Email Open CountsTool to retrieve counts of opened emails.
Get Message StreamTool to retrieve details of a specific message stream by its ID.
Get Opens by PlatformTool to retrieve email open statistics by platform type.
Get Outbound OverviewTool to retrieve outbound email statistics overview.
Get Sent CountsTool to retrieve total count of emails sent out.
Get ServerTool to retrieve details of the current Postmark server.
Get Spam ComplaintsTool to retrieve counts of spam complaints.
Get TemplateTool to retrieve details of a specific template by its ID.
Get Tracked Email CountsTool to retrieve counts of emails with tracking enabled.
Get WebhookTool to retrieve details of a specific webhook by its ID.
List Inbound RulesTool to list all inbound rules (triggers) configured for blocking senders.
List Message StreamsTool to list all message streams for a Postmark server with optional type and archive filtering.
List Outbound Message ClicksTool to list clicks for outbound messages with filtering options.
List Outbound Message OpensTool to retrieve opens for outbound messages with filtering options.
List SuppressionsTool to retrieve the suppression list for a message stream with optional filtering.
List TemplatesTool to list all templates for a Postmark server.
List WebhooksTool to list all webhooks configured for your Postmark account.
Search Inbound MessagesTool to search inbound messages received with optional filtering.
Search Outbound MessagesTool to search outbound messages with filtering by recipient, tag, status, and date range.
Send Batch Templated EmailsTool to send multiple templated emails in a single batch API call.
Unarchive Message StreamTool to unarchive a previously archived message stream.
Update Message StreamTool to update a message stream configuration in Postmark.
Validate TemplateTool to validate a Postmark template.

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

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

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 pydantic-ai python-dotenv

Install the required libraries.

What's happening:

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

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

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 Postmark
  • MCPServerStreamableHTTP connects to the Postmark MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant

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 Postmark
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["postmark"],
    )
    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 Postmark 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

Initialize the Pydantic AI Agent

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

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 Postmark.\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
  • Postmark API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns

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 Postmark 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 Postmark
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["postmark"],
    )
    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
    postmark_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[postmark_mcp],
        instructions=(
            "You are a Postmark assistant. Use Postmark 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 Postmark.\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 Postmark through Composio's Tool Router. With this setup, your agent can perform real Postmark 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 + Postmark for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.

How to build Postmark MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Postmark MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Postmark MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Postmark MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Postmark MCP with Claude Cowork

Codex logo

Codex

Use Postmark MCP with Codex

OpenClaw logo

OpenClaw

Use Postmark MCP with OpenClaw

Hermes logo

Hermes

Use Postmark MCP with Hermes

CLI logo

CLI

Use Postmark MCP with CLI

Google ADK logo

Google ADK

Use Postmark MCP with Google ADK

LangChain logo

LangChain

Use Postmark MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Postmark MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Postmark MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Postmark MCP with LlamaIndex

CrewAI logo

CrewAI

Use Postmark MCP with CrewAI

FAQ

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

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

Can I use Tool Router MCP with Pydantic AI?

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 Postmark tools.

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

Yes, absolutely. You can configure which Postmark 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 Postmark data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
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.

Get started for freeGet a demo↗