How to Use the NeetoCal MCP in OpenAI Agents SDK

Q: How do I connect NeetoCal to the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp object with your NeetoCal endpoint URL and pass it to your Agent constructor in the mcpservers array. Set cacheToolsList=True to speed up tool discovery.

Q: What happens if a user tries to book an unavailable slot?

The agent runs getslots first to verify availability. If a user forces an invalid time, the createbooking tool returns an error. You can configure your agent's guardrails to catch this and prompt the user for a valid time.

Wire NeetoCal scheduling straight into your OpenAI Agents SDK production system with zero configuration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NeetoCal MCP to OpenAI Agents SDK

Create your Vinkius account to connect NeetoCal 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 NeetoCal with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

NeetoCal MCP Server Integration

Your OpenAI Agents SDK agents manage NeetoCal calendars using the `list_calendars` and `get_slots` tools. Instead of building custom API wrappers, your agent pulls available times directly from the MCP Server. It checks existing schedules to prevent double-booking before suggesting slots to users. When a user picks a time, the agent fires `create_booking` to lock it in. Because you use OpenAI's framework, you can wrap these actions in strict guardrails to ensure the agent never books outside business hours or bypasses required email fields.

Link Generation & Modifications

The `get_scheduling_link` tool generates precise meeting URLs for your users. You hand the agent a set of parameters, and it returns a valid NeetoCal link that you can drop into a chat interface or an email thread. If plans change, the agent handles the fallout. It uses `reschedule_booking` to move the appointment or `cancel_booking` to wipe it completely. Every action traces back to your OpenAI dashboard, so you know exactly when and why an agent modified a schedule.

Status Checks & Agent Handoffs

Agents check their connection to the scheduling backend using the `check_neetocal_status` tool. This happens before they attempt any read or write operations. If the endpoint is down, the agent catches the error early instead of failing mid-conversation. You can also build specialized handoff systems. A triage agent qualifies a lead and then passes the context to a booking agent. That second agent runs `list_availabilities` and `list_bookings` to find the right account executive and schedule the demo without dropping the thread.

Setup guide

Set up NeetoCal 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 NeetoCal tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NeetoCal 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="NeetoCal Agent",
            instructions="You have access to NeetoCal 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 NeetoCal. 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 NeetoCal 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 NeetoCal MCP in OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` object with your NeetoCal endpoint URL and pass it to your Agent constructor in the `mcp_servers` array. Set `cacheToolsList=True` to speed up tool discovery.

Yes. Once you pass the MCP Server to the agent, it maps all twelve tools automatically. You do not have to manually define the schema for operations like `get_booking` or `list_scheduling_links`.

Every tool execution logs directly to your OpenAI dashboard. You can inspect the exact payload sent to `create_booking` and the response returned by the API. This makes debugging failed appointments straightforward.

The agent runs `get_slots` first to verify availability. If a user forces an invalid time, the `create_booking` tool returns an error. You can configure your agent's guardrails to catch this and prompt the user for a valid time.

This integration processes calendar metadata, booking IDs, and attendee email addresses. The server operates ephemerally within a V8 Isolate Sandbox. Auth requires a single endpoint token, keeping raw credentials out of your agent's memory.

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