Can the agent place an outbound phone call for me?

Yes! Through the `createPhoneCallTool`, you can ask your agent: `Initiate a phone call to +15551234567 using our 'Sales Assistant' persona`. It will format the payload correctly and instruct Vapi to dial the human using the specified AI persona.

How can I read the transcript of an old automated voice call?

Just tell your chat assistant: `fetch the transcript details for call ID '3fbea5x...'`. The `getCallTool` reaches into Vapi, extracts the raw audio-to-text transcript logs, and the assistant can even summarize the entire human-to-AI interaction for you.

Can I tweak system prompts or models sequentially in my chat editor?

Yes, especially if you're in an IDE like Cursor. You can iterate: `Update Assistant 'Agent A' to use GPT-4o and set its prompt to 'Always be highly overly enthusiastic'`. The agent will use the `updateAssistantTool` to reconfigure the live voice persona instantly.

Vapi MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Vapi
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Vapi through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Vapi Assistant",
            instructions=(
                "You help users interact with Vapi. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Vapi"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Vapi MCP Server

Connect your Vapi account to any AI agent and bring the power of automated voice communication into your standard conversational workspace.

The OpenAI Agents SDK auto-discovers all 10 tools from Vapi through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries Vapi, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Phone Calling — Send commands instructing the agent to place outbound human-like phone calls and establish web ringing connections through Vapi's PSTN/WebRTC capabilities.
Call Transcripts — Search through recent call logs, retrieve call details natively, and pull raw voice-to-text transcripts or conversation metrics.
Persona Engineering — Ask your chat agent to build new Vapi assistants, update their system prompts, change its specific model, or mutate Voice IDs on the fly.
Squad Routing — List available telephony numbers, tools, and multi-agent squads natively to configure advanced conversational pathways.

The Vapi MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Vapi to OpenAI Agents SDK via MCP

Follow these steps to integrate the Vapi MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Vapi

Why Use OpenAI Agents SDK with the Vapi MCP Server

OpenAI Agents SDK provides unique advantages when paired with Vapi through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Vapi + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Vapi MCP Server delivers measurable value.

Automated workflows: build agents that query Vapi, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries Vapi, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Vapi tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Vapi to resolve tickets, look up records, and update statuses without human intervention

Vapi MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Vapi to OpenAI Agents SDK via MCP:

create_assistant

Provide configuration for transcriber, model, and voice as a JSON string. Create a new Voice AI assistant persona

create_phone_call

Provide the phone number ID and customer details. Start a new outbound phone call via Vapi

create_web_call

Returns a web call configuration. Generate a new web-based voice call link

get_call_details

Retrieves details, transcripts, and metrics for a specific call

list_agent_tools

List all tools available to Vapi assistants

list_assistants

List all Voice AI assistants configured in Vapi

list_calls

List recent and active voice calls managed by Vapi

list_phone_numbers

List all phone numbers connected to Vapi

list_squads

List all multi-agent squads

update_assistant

Update an existing assistant configuration

Example Prompts for Vapi in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Vapi immediately.

"List all our configured Voice assistants and their IDs."

"Get the details and full transcript for call ID 'vapi1234'."

"Update assistant 'Bot Support' to change its `model.model` parameter to `gpt-4o-mini`."

Troubleshooting Vapi MCP Server with OpenAI Agents SDK

Common issues when connecting Vapi to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Vapi + OpenAI Agents SDK FAQ

Common questions about integrating Vapi MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.