How to integrate Scheduleonce MCP with OpenAI Agents SDK

GET STARTED FOR FREE
Framework Integration Gradient
Scheduleonce Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Scheduleonce to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Scheduleonce agent that can book a meeting with john doe, list all upcoming bookings this week, cancel tomorrow's meeting with client through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Scheduleonce account through Composio's Scheduleonce MCP server.

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

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Scheduleonce
  • Configure an AI agent that can use Scheduleonce as a tool
  • Run a live chat session where you can ask the agent to perform Scheduleonce operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

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

The Scheduleonce MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Scheduleonce account. It provides structured and secure access so your agent can perform Scheduleonce operations on your behalf.

Supported Tools & Triggers

Tools
Book Time SlotTool to book a time slot on a booking calendar in OnceHub.
Cancel BookingTool to cancel a booking by ID in OnceHub.
Create ContactTool to create a new contact in ScheduleOnce.
Create One-Time Link for Booking CalendarTool to create a one-time booking link for a booking calendar in OnceHub.
Create UserTool to create a new user account in OnceHub.
Delete ContactTool to delete a contact by ID from OnceHub.
Delete UserTool to delete a user account from OnceHub.
Get Available Time SlotsTool to retrieve available time slots for a booking calendar from OnceHub.
Get Single BookingTool to retrieve a single booking by ID from OnceHub.
Get Single Booking CalendarTool to retrieve a single booking calendar by ID from OnceHub.
Get Single ContactTool to retrieve a single contact by ID from OnceHub.
Get Single Master PageTool to retrieve a single master page by ID from OnceHub.
Get Single UserTool to retrieve a single user by ID from OnceHub.
Get User Scheduling AvailabilityTool to get user scheduling availability from OnceHub.
List All Booking CalendarsTool to list all booking calendars in the account.
List All Booking PagesTool to list all booking pages in the account.
List All BookingsTool to list all bookings in the account.
List All ContactsTool to list all contacts in the OnceHub account.
List All Event TypesTool to list all event types in the account.
List All Master PagesTool to list all master pages in the account.
List All TeamsTool to list all teams in the OnceHub account.
List All UsersTool to list all users in the OnceHub account.
Mark Booking as No-ShowTool to mark a completed booking as no-show in OnceHub.
Test API KeyTool to validate API key authentication for OnceHub.
Update ContactTool to update an existing contact in ScheduleOnce.
Update UserTool to update an existing user in OnceHub.
Update User Scheduling AvailabilityTool to update user scheduling availability in OnceHub.

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

What is Tool Router?

Composio's Tool Router 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 Tool Router

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

How the Tool Router works

The Tool Router 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:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Scheduleonce project
  • Some knowledge of Python or Typescript

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

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Scheduleonce.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Scheduleonce Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["scheduleonce"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only scheduleonce.
  • The router checks the user's Scheduleonce connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Scheduleonce.
  • This approach keeps things lightweight and lets the agent request Scheduleonce tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Scheduleonce. "
        "Help users perform Scheduleonce operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Scheduleonce and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Scheduleonce operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Scheduleonce.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Scheduleonce and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["scheduleonce"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Scheduleonce. "
        "Help users perform Scheduleonce operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Scheduleonce MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Scheduleonce.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Scheduleonce MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Scheduleonce MCP with Claude Agent SDK

Google ADK

Google ADK

Use Scheduleonce MCP with Google ADK

LangChain

LangChain

Use Scheduleonce MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Scheduleonce MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Scheduleonce MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Scheduleonce MCP with LlamaIndex

CrewAI

CrewAI

Use Scheduleonce MCP with CrewAI

Claude Code

Claude Code

Use Scheduleonce MCP with Claude Code

Codex

Codex

Use Scheduleonce MCP with Codex

FAQ

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

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

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK 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 Scheduleonce tools.

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

Yes, absolutely. You can configure which Scheduleonce 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 Scheduleonce 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.

Book a call↗Get started for free