How to Use the Magic Minutes MCP in OpenAI Agents SDK

Q: How do I connect the Magic Minutes MCP Server to the OpenAI Agents SDK?

Install the pip package and initialize MCPServerStreamableHttp with your endpoint token. Pass it to the Agent constructor via the mcpservers array. The framework auto-discovers the tools immediately.

Q: Can the OpenAI Agents SDK validate tasks before Magic Minutes creates them?

Yes. The SDK enforces strict guardrails before invoking createtask. You define the safety constraints, and the framework blocks any malformed payloads.

Q: What happens if the MCP endpoint fails while my agent is running?

Your agent calls checkapihealth to verify connectivity. If the server drops, the SDK handles the retry logic and logs the error in your tracing dashboard.

Build production-ready meeting agents with the OpenAI Agents SDK and the Magic Minutes MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Magic Minutes MCP to OpenAI Agents SDK

Create your Vinkius account to connect Magic Minutes 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 Magic Minutes with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate action items with the OpenAI Agents SDK

This MCP Server exposes `list_meetings` and `get_meeting_minutes` directly to your production agents. You point the SDK at your meeting data and let the agent parse the raw transcripts. The OpenAI framework auto-discovers these tools without manual schema configuration. When your agent finds an unassigned action item, it calls `create_task` to push it to your backlog. Built-in guardrails validate the task parameters before execution. You track exactly which agent assigned which task using the OpenAI tracing dashboard.

Distribute meeting context across specialized agents

Your agent uses `get_meeting_details` to pull the exact context from your calendar. Instead of building one massive bot, you hand off the data to specialized agents. One agent reads the minutes, while another extracts the decisions. You then trigger `list_meeting_attendees` to see who actually showed up. The SDK manages state across these handoffs. Your agents run in production with strict safety boundaries around who they contact.

Manage contacts and webhooks programmatically

The server provides `list_contacts` and `list_folders` for your agent to navigate your company directory. It pulls the right user IDs before assigning work. You avoid hardcoding employee names into your logic. You handle setup through the MCP protocol by initializing `MCPServerStreamableHttp`. Pass it to the Agent constructor and set cacheToolsList to true for faster boot times. Your agent also checks `list_webhooks` to see where downstream notifications fire.

Setup guide

Set up Magic Minutes 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 Magic Minutes tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the pip package and initialize `MCPServerStreamableHttp` with your endpoint token. Pass it to the Agent constructor via the `mcp_servers` array. The framework auto-discovers the tools immediately.

Yes. The SDK enforces strict guardrails before invoking `create_task`. You define the safety constraints, and the framework blocks any malformed payloads.

Your agent calls `check_api_health` to verify connectivity. If the server drops, the SDK handles the retry logic and logs the error in your tracing dashboard.

The server feeds raw meeting data into the context window. You easily pass the output from `get_meeting_minutes` between specialized agents using native handoff functions.

The server processes raw meeting audio transcripts and attendee lists. Vinkius runs this in a V8 Isolate Sandbox. The environment is ephemeral, meaning your internal conversations never persist after the agent finishes its run.

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