SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Calendarhero MCP with Pydantic AI

Connect Pydantic AI to Calendarhero MCP. Schedule a meeting with your project team, list all meetings i have this week, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Calendarhero logoCalendarhero
Api Key

Calendarhero is a powerful scheduling platform that streamlines your calendar management across multiple services. It helps you efficiently schedule, reschedule, and organize meetings without the back-and-forth.

38 Tools

Introduction

This guide walks you through connecting Calendarhero to Pydantic AI using the Composio tool router. By the end, you'll have a working Calendarhero agent that can create meeting requests, manage contacts, list meeting types and calendars, send reminders, and message the scheduling assistant through natural language commands.

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

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

Also integrate Calendarhero with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic 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 Calendarhero
  • 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 Calendarhero 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 Calendarhero MCP server, and what's possible with it?

The Calendarhero MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Calendarhero account. It provides structured and secure access to your calendar management tools, so your agent can schedule meetings, manage contacts, fetch meeting details, and access your calendar integrations on your behalf.

  • Automated meeting scheduling and requests: Easily have your agent schedule new meetings, select participants, set time ranges, and include extra meeting details in just a few steps.
  • Contact creation and management: Let the agent create new contacts or fetch existing ones, so scheduling is always quick and accurate.
  • Meeting details retrieval: Ask your agent to fetch specific meeting details or get a list of all meetings within a defined timeframe, keeping you up-to-date.
  • Access and manage calendar integrations: Direct your agent to list all connected calendars, add new integrations, or access available calendars for streamlined scheduling.
  • Template and meeting type discovery: Quickly retrieve available meeting templates and types, letting your agent optimize scheduling based on your preferences and routines.

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

Add Calendar Connection

Add a new calendar directory/connection to the user's CalendarHero account.

Create Contact

Creates a new contact in CalendarHero with the provided contact information.

Create Meeting Request V2

Tool to create a new meeting request in CalendarHero.

Create Webhook

Creates or updates a webhook for a specific event type in CalendarHero.

Delete Contact

Tool to delete a contact from CalendarHero by its unique identifier.

Delete Meeting Task

Tool to delete a meeting task/request from CalendarHero.

Delete Meeting Type

Tool to delete a meeting type from the authenticated user's CalendarHero account.

Delete User Directory

Tool to delete a user directory by its UUID.

Delete Webhook

Tool to delete a webhook subscription for a specific event type.

Fetch Contact

Fetch Contact

Fetch Meeting Details

Fetches meeting details for a specified time range.

Fetch User Profile

Tool to fetch the profile details of the authenticated user.

Get Assistant Message

Tool to retrieve a reply message from the CalendarHero assistant.

Get Contact Count

Tool to get the total count of contacts in CalendarHero.

Get Meeting Categories

Retrieves the user's meeting categories' stats for a specified time period.

Get Meeting Tasks

Retrieves the user's meeting requests/tasks from CalendarHero.

Get Search Result

Tool to get a search result by ID.

Get User Directory

Tool to retrieve a user's directory by its unique identifier.

Get User Organization

Tool to retrieve the authenticated user's organization details.

Get User Savings

Tool to retrieve the authenticated user's savings information from CalendarHero.

Get Webhook Configuration

Retrieves webhook configuration for a specific meeting or contact event type.

Get Webhook Sample

Tool to retrieve a sample webhook payload for a specific event type.

List Meeting Templates

Lists the authenticated user's meeting templates, which are reusable scheduling configurations.

List Meeting Types

Retrieves all meeting types configured for the authenticated CalendarHero user.

List User Calendars

Tool to list all calendar integrations connected to a user's CalendarHero account.

List User Directories

Tool to retrieve all directories configured for a user.

Search Contact

Tool to search for existing contacts.

Search Integrations

Tool to search across all user integrations for a query term.

Send Assistant Message

Tool to send a user's message into the CalendarHero assistant.

Send Reminder

Sends an email reminder to all contacts/participants about a scheduled meeting request.

Update Contact

Updates an existing CalendarHero contact by ID, including details such as name, title, organization, and phone numbers.

Update Meeting Types

Tool to update meeting type configurations for the authenticated CalendarHero user.

Update Restricted Apps

Updates the authenticated user's restricted apps settings using a list of app identifiers.

Update User

Tool to update the authenticated user's profile information.

Update User Address

Tool to update the authenticated user's address settings by providing latitude and longitude coordinates.

Update User Directory

Tool to update a user's directory in CalendarHero.

Update User Info

Updates the authenticated user's info settings in CalendarHero.

Update Work Location

Tool to update the user's work location settings in CalendarHero.

FRAMEWORKS

How to build Calendarhero MCP Agent with another framework

Claude Code logo

Claude Code

Use Calendarhero MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Calendarhero MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Calendarhero MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Calendarhero MCP with Claude Agent SDK

Codex logo

Codex

Use Calendarhero MCP with Codex

OpenClaw logo

OpenClaw

Use Calendarhero MCP with OpenClaw

Hermes logo

Hermes

Use Calendarhero MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Calendarhero MCP with Atomic Agent

Google ADK logo

Google ADK

Use Calendarhero MCP with Google ADK

LangChain logo

LangChain

Use Calendarhero MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Calendarhero MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Calendarhero MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Calendarhero MCP with LlamaIndex

CrewAI logo

CrewAI

Use Calendarhero MCP with CrewAI

AutoGen logo

AutoGen

Use Calendarhero MCP with AutoGen

FAQ

Frequently asked questions

Start with Calendarhero.It takes 30 seconds.

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

Start building