How to Use the Uniphore Conversation AI MCP in OpenAI Agents SDK

Q: How do I search meetings using Uniphore Conversation AI and OpenAI Agents SDK?

You use the searchmeetings tool. You pass in keywords or topics, and the agent filters through all available records to find relevant calls. This prevents your agent from having to process every single conversation.

Q: What data types can I get when using Uniphore Conversation AI and OpenAI Agents SDK?

You can grab full transcripts with gettranscript, or you can run a high-level summary using getmeetingsummary. The agent handles both, letting you pick the depth of detail you need for your task.

Q: How do I handle meeting details using Uniphore Conversation AI and OpenAI Agents SDK?

First, run listmeetings to get IDs. Then, use those IDs with getmeeting to pull specific metadata about that conversation. This two-step process ensures your agent always has the correct context before running deeper queries.

Turn recorded meetings into actionable insights with the 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 Uniphore Conversation AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Uniphore Conversation AI 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 Uniphore Conversation AI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Extracting Key Action Items via MCP Server

Run `get_action_items` to pull out specific tasks assigned during a call. You get structured data detailing who owns the task and when it's due, so your agents don't have to read through pages of text. This saves time by going straight to the outcome. Instead of asking for a summary, you ask for the next steps, which is exactly what most teams need after a meeting.

Searching and Listing Meetings

Need to find context? Use `list_meetings` to get all available IDs first. Then, run `search_meetings` with specific keywords or topics to narrow down the pool of calls. It's a reliable way to feed your agent exactly what it needs without guesswork. This setup works perfectly for agents that need to audit conversations over time before they can summarize anything.

Deep Dive into Conversation Analytics

The `get_meeting_analytics` tool pulls back conversation metrics and insights. This data goes beyond just summarizing the talk—you see *how* the meeting went, which is critical for performance reviews or process improvement. Your agents can then cross-reference these analytics against other records to build a fuller picture of team health.

Setup guide

Set up Uniphore Conversation AI 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 Uniphore Conversation AI tools at runtime.
3

Create your Agent

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

Run the agent

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

You use the `search_meetings` tool. You pass in keywords or topics, and the agent filters through all available records to find relevant calls. This prevents your agent from having to process every single conversation.

You can grab full transcripts with `get_transcript`, or you can run a high-level summary using `get_meeting_summary`. The agent handles both, letting you pick the depth of detail you need for your task.

Yep. Since it uses a standard MCP interface, the agents auto-discover all the tools right out of the box. You don't have to write any custom integration code; you just pass the server into your agent constructor.

First, run `list_meetings` to get IDs. Then, use those IDs with `get_meeting` to pull specific metadata about that conversation. This two-step process ensures your agent always has the correct context before running deeper queries.

This MCP Server touches meeting transcripts and full text records. The system processes this sensitive information to extract structured insights, ensuring you get actionable items without needing to manually parse the raw conversation stream.

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