How to Use the Mio MCP in OpenAI Agents SDK

Q: Can my agent check call history in OpenAI Agents SDK using Mio?

Yes, your agent can call listcalls to fetch historical logs and then use getcalldetails to inspect a specific record. This allows the agent to make decisions based on previous customer interactions.

Trigger real-time voice calls and retrieve transcripts directly from your production OpenAI Agents SDK pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mio MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate voice calls with your OpenAI Agents SDK

`start_ai_call` kicks off automated voice sessions directly from your python agent script. You pass the target number and select from the options returned by `list_available_voices` to match your brand's tone. The agent controls the entire lifecycle, dropping the connection with `terminate_call` when the task finishes. This setup runs inside the secure Vinkius sandbox, ensuring your API keys stay hidden. Connecting your agent to an MCP Server allows OpenAI's SDK to handle agent handoffs natively, so you can have a specialized routing agent pass the active session to a billing agent that checks remaining funds via `get_credit_balance` before placing the call.

Pull call text and summaries post-call

`get_call_transcript` pulls the full text log of any completed conversation for immediate analysis. Your agent reads this transcript to extract action items, customer sentiment, or follow-up tasks without requiring human intervention. If you only need a quick overview, `get_call_summary` provides a structured recap of the dialogue. Running this through the MCP Server means your agents don't have to parse raw audio files or manage complex transcription pipelines. The raw text feeds straight into the OpenAI tracing dashboard, giving you a clear view of how your agent interpreted the conversation.

Real-time events with managed webhooks

`create_webhook` registers a new endpoint to alert your system the moment a call status changes. You monitor active connections with `list_webhooks` and clean up old endpoints using `delete_webhook` when they are no longer needed. This keeps your agentic loops event-driven instead of forcing them to waste resources on constant polling. This event-driven pattern keeps your OpenAI agents responsive. Instead of keeping a container running indefinitely, your agent wakes up only when an inbound event triggers, saving compute costs across your entire infrastructure.

Setup guide

Set up Mio 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 Mio tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK via pip and initialize the server using the streamable HTTP transport class. You pass the Vinkius endpoint URL directly into your agent configuration block, allowing auto-discovery of all twelve communication tools.

Yes, your agent can call `list_calls` to fetch historical logs and then use `get_call_details` to inspect a specific record. This allows the agent to make decisions based on previous customer interactions.

The SDK validates all tool inputs against the server's schema before execution. If an agent attempts to pass an invalid phone number to `start_ai_call`, the SDK's built-in guardrails block the request before it hits the network.

You can register, view, and remove webhooks programmatically. This MCP setup lets your agent manage its own event listeners on the fly using `create_webhook` and `delete_webhook`.

All transcripts, call logs, and webhook configurations are processed inside isolated V8 sandboxes. Vinkius uses ephemeral execution environments that immediately destroy session data once the tool execution completes, preventing persistent storage of sensitive communications.

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