Calendarhero with LlamaIndex

How to integrate Calendarhero MCP with LlamaIndex

Trusted by

GET STARTED FOR FREE GET A DEMO

30 min · no commitment · see it on your stack

Introduction Also integrate Calendarhero with TL;DR What is LlamaIndex What is the Calendarhero MCP server Supported Tools & Triggers Creating MCP Server - Stand-alone vs Composio SDK Step-by-step Guide Complete Code Conclusion How to build Calendarhero MCP Agent with another framework Explore Other Toolkits FAQ

Connect Calendarhero without Auth hassles

We manage OAuth, API Key, token refresh, and scopes, you just build.

Try for Free

Introduction

This guide walks you through connecting Calendarhero to LlamaIndex using the Composio tool router. By the end, you'll have a working Calendarhero agent that can schedule a meeting with your project team, list all meetings i have this week, fetch details for your next scheduled meeting through natural language commands.

This guide will help you understand how to give your LlamaIndex 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

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK LangChain Vercel AI SDK Mastra AI CrewAI

TL;DR

Here's what you'll learn:

Set your OpenAI and Composio API keys
Install LlamaIndex and Composio packages
Create a Composio Tool Router session for Calendarhero
Connect LlamaIndex to the Calendarhero MCP server
Build a Calendarhero-powered agent using LlamaIndex
Interact with Calendarhero through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

ReAct Agent: Reasoning and acting pattern for tool-using agents
MCP Tools: Native support for Model Context Protocol
Context Management: Maintain conversation context across interactions
Async Support: Built 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.

Supported Tools & Triggers

Tools

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

Create ContactCreates a new contact in CalendarHero with the provided contact information.

Create Meeting Request V2Tool to create a new meeting request in CalendarHero.

Create WebhookCreates or updates a webhook for a specific event type in CalendarHero.

Delete ContactTool to delete a contact from CalendarHero by its unique identifier.

Delete Meeting TaskTool to delete a meeting task/request from CalendarHero.

Delete Meeting TypeTool to delete a meeting type from the authenticated user's CalendarHero account.

Delete User DirectoryTool to delete a user directory by its UUID.

Delete WebhookTool to delete a webhook subscription for a specific event type.

Fetch ContactFetch Contact

Fetch Meeting DetailsTool to fetch details for meetings within a specified timeframe.

Fetch User ProfileTool to fetch the profile details of the authenticated user.

Get Assistant MessageTool to retrieve a reply message from the CalendarHero assistant.

Get Contact CountTool to get the total count of contacts in CalendarHero.

Get Meeting CategoriesRetrieves the user's meeting categories' stats for a specified time period.

Get Meeting TasksRetrieves the user's meeting requests/tasks from CalendarHero.

Get Search ResultTool to get a search result by ID.

Get User DirectoryTool to retrieve a user's directory by its unique identifier.

Get User OrganizationTool to retrieve the authenticated user's organization details.

Get User SavingsTool to retrieve the authenticated user's savings information from CalendarHero.

Get Webhook ConfigurationTool to get webhook configuration for a specific event type.

Get Webhook SampleTool to retrieve a sample webhook payload for a specific event type.

List Meeting TemplatesRetrieves all meeting templates (reusable meeting configurations) for the authenticated user.

List Meeting TypesRetrieves all meeting types configured for the authenticated CalendarHero user.

List User CalendarsTool to list all calendar integrations connected to a user's CalendarHero account.

List User DirectoriesTool to retrieve all directories configured for a user.

Search ContactTool to search for existing contacts.

Search IntegrationsTool to search across all user integrations for a query term.

Send Assistant MessageTool to send a user's message into the CalendarHero assistant.

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

Update ContactUpdates an existing contact in CalendarHero with new information.

Update Meeting TypesTool to update meeting type configurations for the authenticated CalendarHero user.

Update Restricted AppsTool to update the authenticated user's restricted apps settings.

Update UserTool to update the authenticated user's profile information.

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

Update User DirectoryTool to update a user's directory in CalendarHero.

Update User InfoUpdates the authenticated user's info settings in CalendarHero.

Update Work LocationTool to update the user's work location settings in CalendarHero.

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:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before you begin, make sure you have:

Python 3.8/Node 16 or higher installed
A Composio account with the API key
An OpenAI API key
A Calendarhero account and project
Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Calendarhero

OpenAI API key (OPENAI_API_KEY)

Go to the OpenAI dashboard
Create an API key if you don't have one
Assign it to OPENAI_API_KEY in .env

Composio API key and user ID

Log into the Composio dashboard
Copy your API key from Settings
- Use this as COMPOSIO_API_KEY
Pick a stable user identifier (email or ID)
- Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

composio-llamaindex: Composio's LlamaIndex integration
llama-index: Core LlamaIndex framework
llama-index-llms-openai: OpenAI LLM integration
llama-index-tools-mcp: MCP client for LlamaIndex
python-dotenv: Environment variable management

Set environment variables

bash

OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

Authenticate with OpenAI's GPT-5 model
Connect to Composio's Tool Router
Identify your Composio user session for Calendarhero access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called calendarhero_llamaindex_agent.py and import the required modules:

Key imports:

asyncio: For async/await support
Composio: Main client for Composio services
LlamaIndexProvider: Adapts Composio tools for LlamaIndex
ReActAgent: LlamaIndex's reasoning and action agent
BasicMCPClient: Connects to MCP endpoints
McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["calendarhero"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Calendarhero actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Calendarhero actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

We create a Composio client using your API key and configure it with the LlamaIndex provider
We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, calendarhero)
The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
LlamaIndex will connect to this endpoint to dynamically discover and use the available Calendarhero tools.
The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

We're creating a direct terminal interface to chat with your Calendarhero database
The LLM's responses are streamed to the CLI for faster interaction.
The agent uses context to maintain conversation history
You can type 'quit' or 'exit' to stop the chat loop gracefully
Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

We're orchestrating the entire application flow
The agent gets built with proper error handling
Then we kick off the interactive chat loop so you can start talking to Calendarhero

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Calendarhero, then start asking questions.

Complete Code

Here's the complete code to get you started with Calendarhero and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["calendarhero"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Calendarhero actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Calendarhero actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Calendarhero to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:

Tool Router dynamically exposes Calendarhero tools through an MCP endpoint
LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
The agent becomes more capable without increasing prompt size
Async Python provides clean, efficient execution of agent workflows

You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Calendarhero MCP Agent with another framework

OpenAI Agents SDK

Use Calendarhero MCP with OpenAI Agents SDK

Claude Agent SDK

Use Calendarhero MCP with Claude Agent SDK

Claude Code

Use Calendarhero MCP with Claude Code

Claude Cowork

Use Calendarhero MCP with Claude Cowork

Codex

Use Calendarhero MCP with Codex

OpenClaw

Use Calendarhero MCP with OpenClaw

Hermes

Use Calendarhero MCP with Hermes

CLI

Use Calendarhero MCP with CLI

Google ADK

Use Calendarhero MCP with Google ADK

LangChain

Use Calendarhero MCP with LangChain

Vercel AI SDK

Use Calendarhero MCP with Vercel AI SDK

Mastra AI

Use Calendarhero MCP with Mastra AI

CrewAI

Use Calendarhero MCP with CrewAI

Explore Other Toolkits

Google Calendar

Oauth2

Google Calendar is a time management service for scheduling meetings, events, and reminders. It streamlines personal and team organization with integrated notifications and sharing options.

Apaleo

Oauth2

Apaleo is a cloud-based property management platform for hospitality businesses. It centralizes reservations, billing, and daily operations for smoother hotel management.

Appointo

Api Key

Appointo is an appointment booking platform for Shopify stores. It lets businesses add online scheduling to their websites with zero coding.

TOOLKIT MARKETPLACE

FAQ

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

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

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex 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 Calendarhero tools.

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

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

Used by agents from

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 free Get a demo↗

Harsha GaddipatiCo-founder, Slashy

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

Abhi AryaCo-founder, Opennote

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 has immensely helped in keeping new users on the platform.

Nirman DaveCEO, Zams

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

Ryan YuFounder, Extra Thursday

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

Tomisin JenrolaFounder & CEO, SwarmZero

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

Jerome LeclancheCo-Founder, Ingram Technologies

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.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

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.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

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.

How to integrate Calendarhero MCP with LlamaIndex

Table of Contents

Connect Calendarhero without Auth hassles

Introduction

Also integrate Calendarhero with

TL;DR

What is LlamaIndex?

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

Supported Tools & Triggers

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

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI, Composio, and Calendarhero

Installing dependencies

Set environment variables

Import modules

Load environment variables and initialize Composio

Create a Tool Router session and build the agent function

Create an interactive chat loop

Define the main entry point

Run the agent

Complete Code

Conclusion

How to build Calendarhero MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

LangChain

Vercel AI SDK

Mastra AI

CrewAI

Explore Other Toolkits

Google Calendar

Apaleo

Appointo

FAQ

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

Can I use Tool Router MCP with LlamaIndex?

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

How safe is my data with Composio Tool Router?

Used by agents from

Never worry about agent reliability