How to Use the MeetingPulse MCP in OpenAI Agents SDK

Q: How do I initialize the MeetingPulse MCP Server within the OpenAI Agents SDK?

Install openai-agents and instantiate MCPServerStreamableHttp using your Vinkius endpoint. Pass the server instance directly into your Agent constructor within an async context manager, and the SDK handles the rest.

Q: Can my OpenAI Agents SDK tools handle live Q&A updates from MeetingPulse?

Yes, your agent can call listqasessions to pull live audience questions during an active event. This lets you build real-time moderation or summarization workflows directly inside your agent system.

Q: Can I trace MeetingPulse tool executions on the OpenAI dashboard?

Absolutely. Every time your OpenAI Agents SDK calls listpolls or listattendees, the complete input parameters and raw JSON payloads are logged directly in your OpenAI run traces for debugging.

Build production-grade OpenAI Agents SDK systems that pull real-time audience feedback and analytics from MeetingPulse.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MeetingPulse MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run secure audience data lookups in OpenAI Agents SDK

Inspect raw event engagement by running `get_meeting_analytics` through the OpenAI Agents SDK, where built-in MCP guardrails validate the target meeting ID before execution. This prevents the agent from making arbitrary API requests or fetching data from unauthorized meeting IDs during live runs. The agent pulls the exact attendee feedback using `get_poll_details` and presents it to your team, while the OpenAI dashboard traces every single step of the data retrieval. This keeps your production environment secure without adding manual validation boilerplate to your codebase.

Coordinate multi-agent handoffs for event reporting

Coordinate multi-agent handoffs by using `list_meetings` to discover active sessions and route tasks between specialized agents. Your primary routing agent identifies the correct event and immediately passes control to specialized sub-agents optimized for specific data types. The poll analyst agent focuses entirely on extracting poll responses via `list_polls` while the Q&A agent runs `list_qa_sessions` to compile audience questions. This division of labor keeps your OpenAI Agents SDK system fast and prevents context window bloat during massive town halls.

Auto-discover this MCP Server in your agent pipelines

Expose all ten audience interaction capabilities instantly by registering the MeetingPulse MCP Server in your streamable HTTP setup. This eliminates the need to write custom API wrappers for your audience engagement tools, letting your OpenAI Agents SDK auto-discover all tools with zero manual configuration. Your agent immediately gains the ability to locate files with `list_meeting_files` or search historical events via `search_meetings`. You get a production-ready audience intelligence pipeline up and running in minutes, fully monitored through your standard OpenAI tracing dashboard.

Setup guide

Set up MeetingPulse 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 MeetingPulse tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and instantiate `MCPServerStreamableHttp` using your Vinkius endpoint. Pass the server instance directly into your `Agent` constructor within an async context manager, and the SDK handles the rest.

Yes, your agent can call `list_qa_sessions` to pull live audience questions during an active event. This lets you build real-time moderation or summarization workflows directly inside your agent system.

The SDK uses built-in guardrails to validate tool arguments before executing actions like `get_meeting`. You can define strict schemas that prevent the agent from querying unauthorized meeting IDs.

Absolutely. Every time your OpenAI Agents SDK calls `list_polls` or `list_attendees`, the complete input parameters and raw JSON payloads are logged directly in your OpenAI run traces for debugging.

Your meeting files, poll responses, and attendee lists are processed inside an ephemeral, zero-trust V8 sandbox. No audience data is stored on Vinkius, ensuring your meeting analytics remain completely isolated.

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