How to Use the Vapi MCP in OpenAI Agents SDK

Q: How do I list all available tools in Vapi using the OpenAI Agents SDK?

Call listagenttools. This returns every capability exposed by this MCP Server, giving your agent a clear map of what it can actually do.

Q: Does Vapi support multi-step workflows with the OpenAI Agents SDK?

Yep. You've got listsquads which lets you manage groups of agents, allowing for complex handoffs and specialized agent interactions within one workflow.

Q: How can I check my active voice calls with Vapi and the OpenAI Agents SDK?

Just run listcalls. This method gives you a rundown of all recent and currently running voice interactions managed by Vapi. It's quick and reliable.

Run production voice workflows with OpenAI Agents SDK and Vapi.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vapi MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Managing Call Personas with the MCP Server

You configure new Voice AI assistant personas using `create_assistant`, specifying the transcriber, model, and voice. This ensures your agents adopt specific identities before making calls or handling conversations. You can also adjust existing setups when needed. The `update_assistant` tool lets you modify an agent's configuration without having to redeploy the entire system.

Tracking Calls and Metrics for OpenAI Agents SDK

The `get_call_details` tool pulls full transcripts, metrics, and specific data points from any given call. This gives your agent a complete picture of performance after the fact. Need to audit what's available? Use `list_calls` or `list_phone_numbers` to keep track of all recent activity managed by Vapi.

Executing Outbound Calls via MCP Server

Initiate new phone calls directly from your agent logic using `create_phone_call`. You just pass the required phone number ID and customer details, and the call starts. For web-based interactions, `create_web_call` generates a full configuration you can use to start a virtual session.

Setup guide

Set up Vapi 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 Vapi tools at runtime.
3

Create your Agent

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

Run the agent

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

Call `list_agent_tools`. This returns every capability exposed by this MCP Server, giving your agent a clear map of what it can actually do.

Yep. You've got `list_squads` which lets you manage groups of agents, allowing for complex handoffs and specialized agent interactions within one workflow.

Vapi records detailed call transcripts, performance metrics, and full operational logs. All this information is accessible through `get_call_details` for review.

Just run `list_calls`. This method gives you a rundown of all recent and currently running voice interactions managed by Vapi. It's quick and reliable.

This server handles Call metadata, Assistant configurations, Phone numbers, and Transcripts. You can manage all these core assets through its tools.

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