How to Use the Calendly MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK read my Calendly availability?

Yes. Your agent can call getavailabletimes to check open slots for specific event types. It automatically respects the constraints of the date range you specify.

Build production-ready scheduling workflows with Calendly and OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Calendly MCP to OpenAI Agents SDK

Create your Vinkius account to connect Calendly to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Calendly with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect OpenAI Agents SDK to Calendly

Your scheduling agent needs access to real calendars. This MCP integration connects directly to your user profiles and event types. Pass the server endpoint to your agent constructor, and it immediately discovers the tools it needs to book meetings. You get full execution tracing through the OpenAI dashboard. When your agent calls `get_available_times`, you see exactly what parameters it passed. Built-in guardrails prevent rogue actions, so an agent won't trigger `cancel_event` without explicit user confirmation.

Read complex availability data

Finding a meeting time is notoriously difficult for AI. We expose `list_availability` and `get_available_times` to give your agent the exact time slots open for a specific event type. It pulls the raw schedule data within an explicit date range. Handoffs between specialized agents work perfectly here. A sales agent qualifies a lead, then passes the context to a scheduling agent. That second agent runs `list_event_types` to pick the right meeting template and offers exact slots to the user.

Manage scheduled events and invitees

Booking the meeting is only half the job. Your system also needs to track who is showing up. The `list_invitees` tool returns every attendee attached to a specific scheduled event. Because this is a standard MCP Server, the entire workflow stays inside your Python backend. You can pull full details using `get_scheduled_event` with the tracking UUID. If a client reschedules or drops out, your agent can fire `cancel_event` and attach an optional cancellation reason.

Setup guide

Set up Calendly MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Calendly tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Calendly tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Calendly tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Calendly Agent",
            instructions="You have access to Calendly tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Calendly. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Calendly now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Calendly MCP in OpenAI Agents SDK

Initialize the MCP Server using MCPServerStreamableHttp with your Vinkius endpoint. Pass it to your Agent constructor via the mcp_servers parameter. Set cacheToolsList=True to speed up initialization.

Yes. Your agent can call get_available_times to check open slots for specific event types. It automatically respects the constraints of the date range you specify.

The SDK features built-in guardrails. You can configure rules that force the agent to ask for human approval before executing cancel_event.

Multi-agent setups handle this perfectly. You can assign the scheduling tools to a dedicated calendar agent. Other agents in your system can hand off tasks to this specific agent when a user asks to book a meeting.

Vinkius runs this MCP server in an ephemeral V8 Isolate Sandbox. When your agent pulls emails, names, and timezones using list_invitees, the data routes directly to your OpenAI environment. The sandbox destroys itself after the request, leaving zero persistence on our infrastructure.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript