How to integrate Vapi MCP with OpenAI Agents SDK

GET STARTED FOR FREE
Framework Integration Gradient
Vapi Logo
open-ai-agents-sdk Logo
divider

Introduction

This guide walks you through connecting Vapi to the OpenAI Agents SDK using the Composio tool router. By the end, you'll have a working Vapi agent that can start a new outbound call campaign, get transcript from the last agent call, pause all ongoing voice agent sessions through natural language commands.

This guide will help you understand how to give your OpenAI Agents SDK agent real control over a Vapi account through Composio's Vapi MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the necessary dependencies
  • Initialize Composio and create a Tool Router session for Vapi
  • Configure an AI agent that can use Vapi as a tool
  • Run a live chat session where you can ask the agent to perform Vapi operations

What is open-ai-agents-sdk?

The OpenAI Agents SDK is a lightweight framework for building AI agents that can use tools and maintain conversation state. It provides a simple interface for creating agents with hosted MCP tool support.

Key features include:

  • Hosted MCP Tools: Connect to external services through hosted MCP endpoints
  • SQLite Sessions: Persist conversation history across interactions
  • Simple API: Clean interface with Agent, Runner, and tool configuration
  • Streaming Support: Real-time response streaming for interactive applications

What is the Vapi MCP server, and what's possible with it?

The Vapi MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Vapi account. It provides structured and secure access so your agent can perform Vapi operations on your behalf.

Supported Tools & Triggers

Tools
Update AssistantTool to update an existing Vapi assistant configuration.
List CallsTool to list calls from Vapi.
Delete ChatTool to delete a chat by its ID from Vapi.
Get ChatTool to fetch chat details by ID.
Create Analytics QueriesTool to create and execute analytics queries on VAPI data.
Create AssistantTool to create a new Vapi assistant with specified transcriber, voice, and AI model configurations.
Create EvalTool to create an eval for testing conversation flows.
Create OpenAI ChatTool to create an OpenAI-compatible chat using the Vapi API.
Create Phone NumberTool to create a phone number with Vapi.
Create Monitoring PolicyTool to create a monitoring policy in VAPI.
Create Provider ResourceTool to create an 11Labs pronunciation dictionary resource.
Create ScorecardTool to create a scorecard for observability and evaluation.
Delete CallTool to delete a call by its unique identifier.
Delete EvalTool to delete an eval by ID.
Delete Phone NumberTool to delete a phone number from Vapi.
Get EvalTool to retrieve an eval by its ID.
Delete Eval RunTool to delete an eval run by its ID from Vapi.
Update EvalTool to update an existing eval in Vapi.
Get AssistantTool to retrieve a specific assistant by ID from Vapi.
Get CallTool to fetch call details by ID.
Get FileTool to retrieve a file by its ID from Vapi.
Get InsightsTool to retrieve insights from Vapi.
List Monitoring PoliciesTool to retrieve monitoring policies from Vapi.
Get Observability ScorecardTool to list observability scorecards with optional filtering and pagination.
List Provider ResourcesTool to list provider resources from Vapi.
List Structured OutputsTool to list structured outputs with optional filtering.
Get InsightsTool to retrieve insights from VAPI.
List AssistantsTool to list all assistants in your VAPI organization.
List ChatsTool to retrieve a list of chat conversations from VAPI.
List EvalsTool to retrieve a paginated list of evals from Vapi.
List Provider ResourcesTool to retrieve provider resources from Vapi (e.
Update InsightTool to update an existing insight configuration in VAPI.
Create Phone NumberTool to create a phone number with VAPI.
List ScorecardsTool to retrieve a paginated list of scorecards from Vapi.
Create SessionTool to create a new session in Vapi.
List SessionsTool to retrieve a paginated list of sessions from VAPI.
List Structured OutputsTool to list structured outputs with optional filtering and pagination.
Get ToolTool to fetch tool details by ID.
Test Code Tool ExecutionTool to test TypeScript code execution in Vapi's code tool environment.
Update ToolTool to update an existing Vapi tool configuration.
Update Phone NumberTool to update an existing phone number configuration in VAPI.
Upload FileTool to upload a file to Vapi Knowledge Base.

What is the Composio tool router, and how does it fit here?

What is Tool Router?

Composio's Tool Router helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Tool Router

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Tool Router works

The Tool Router follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before starting, make sure you have:
  • Composio API Key and OpenAI API Key
  • Primary know-how of OpenAI Agents SDK
  • A live Vapi project
  • Some knowledge of Python or Typescript

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key

Install dependencies

pip install composio_openai_agents openai-agents python-dotenv

Install the Composio SDK and the OpenAI Agents SDK.

Set up environment variables

bash
OPENAI_API_KEY=sk-...your-api-key
COMPOSIO_API_KEY=your-api-key
USER_ID=composio_user@gmail.com

Create a .env file and add your OpenAI and Composio API keys.

Import dependencies

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession
What's happening:
  • You're importing all necessary libraries.
  • The Composio and OpenAIAgentsProvider classes are imported to connect your OpenAI agent to Composio tools like Vapi.

Set up the Composio instance

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())
What's happening:
  • load_dotenv() loads your .env file so OPENAI_API_KEY and COMPOSIO_API_KEY are available as environment variables.
  • Creating a Composio instance using the API Key and OpenAIAgentsProvider class.

Create a Tool Router session

# Create a Vapi Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["vapi"]
)

mcp_url = session.mcp.url

What is happening:

  • You give the Tool Router the user id and the toolkits you want available. Here, it is only vapi.
  • The router checks the user's Vapi connection and prepares the MCP endpoint.
  • The returned session.mcp.url is the MCP URL that your agent will use to access Vapi.
  • This approach keeps things lightweight and lets the agent request Vapi tools only when needed during the conversation.

Configure the agent

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Vapi. "
        "Help users perform Vapi operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)
What's happening:
  • We're creating an Agent instance with a name, model (gpt-5), and clear instructions about its purpose.
  • The agent's instructions tell it that it can access Vapi and help with queries, inserts, updates, authentication, and fetching database information.
  • The tools array includes a HostedMCPTool that connects to the MCP server URL we created earlier.
  • The headers dict includes the Composio API key for secure authentication with the MCP server.
  • require_approval: 'never' means the agent can execute Vapi operations without asking for permission each time, making interactions smoother.

Start chat loop and handle conversation

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())
What's happening:
  • The program prints a session URL that you visit to authorize Vapi.
  • After authorization, the chat begins.
  • Each message you type is processed by the agent using Runner.run().
  • The responses are printed to the console, and conversations are saved locally using SQLite.
  • Typing exit, quit, or q cleanly ends the chat.

Complete Code

Here's the complete code to get you started with Vapi and open-ai-agents-sdk:

import asyncio
import os
from dotenv import load_dotenv

from composio import Composio
from composio_openai_agents import OpenAIAgentsProvider
from agents import Agent, Runner, HostedMCPTool, SQLiteSession

load_dotenv()

api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")

if not api_key:
    raise RuntimeError("COMPOSIO_API_KEY is not set. Create a .env file with COMPOSIO_API_KEY=your_key")

# Initialize Composio
composio = Composio(api_key=api_key, provider=OpenAIAgentsProvider())

# Create Tool Router session
session = composio.create(
    user_id=user_id,
    toolkits=["vapi"]
)
mcp_url = session.mcp.url

# Configure agent with MCP tool
agent = Agent(
    name="Assistant",
    model="gpt-5",
    instructions=(
        "You are a helpful assistant that can access Vapi. "
        "Help users perform Vapi operations through natural language."
    ),
    tools=[
        HostedMCPTool(
            tool_config={
                "type": "mcp",
                "server_label": "tool_router",
                "server_url": mcp_url,
                "headers": {"x-api-key": api_key},
                "require_approval": "never",
            }
        )
    ],
)

print("\nComposio Tool Router session created.")

chat_session = SQLiteSession("conversation_openai_toolrouter")

print("\nChat started. Type your requests below.")
print("Commands: 'exit', 'quit', or 'q' to end\n")

async def main():
    try:
        result = await Runner.run(
            agent,
            "What can you help me with?",
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")
    except Exception as e:
        print(f"Error: {e}\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "q"}:
            print("Goodbye!")
            break

        result = await Runner.run(
            agent,
            user_input,
            session=chat_session
        )
        print(f"Assistant: {result.final_output}\n")

asyncio.run(main())

Conclusion

This was a starter code for integrating Vapi MCP with OpenAI Agents SDK to build a functional AI agent that can interact with Vapi.

Key features:

  • Hosted MCP tool integration through Composio's Tool Router
  • SQLite session persistence for conversation history
  • Simple async chat loop for interactive testing
You can extend this by adding more toolkits, implementing custom business logic, or building a web interface around the agent.

How to build Vapi MCP Agent with another framework

Claude Agent SDK

Claude Agent SDK

Use Vapi MCP with Claude Agent SDK

Google ADK

Google ADK

Use Vapi MCP with Google ADK

LangChain

LangChain

Use Vapi MCP with LangChain

Vercel AI SDK

Vercel AI SDK

Use Vapi MCP with Vercel AI SDK

Mastra AI

Mastra AI

Use Vapi MCP with Mastra AI

LlamaIndex

LlamaIndex

Use Vapi MCP with LlamaIndex

CrewAI

CrewAI

Use Vapi MCP with CrewAI

Claude Code

Claude Code

Use Vapi MCP with Claude Code

Codex

Codex

Use Vapi MCP with Codex

FAQ

What are the differences in Tool Router MCP and Vapi MCP?

With a standalone Vapi MCP server, the agents and LLMs can only access a fixed set of Vapi tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Vapi and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with OpenAI Agents SDK?

Yes, you can. OpenAI Agents SDK fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Vapi tools.

Can I manage the permissions and scopes for Vapi while using Tool Router?

Yes, absolutely. You can configure which Vapi scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Vapi data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Book a call↗Get started for free