How to integrate Vapi MCP with Autogen

This guide walks you through connecting Vapi to AutoGen 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 AutoGen 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.

Vapi logoVapi
Api Key

Vapi is a voice AI platform for building, testing, and deploying conversational voice agents. It provides real-time responses and seamless integration for voice-driven applications.

42 Tools

Introduction

This guide walks you through connecting Vapi to AutoGen 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 AutoGen 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.

Also integrate Vapi with

TL;DR

Here's what you'll learn:
  • Get and set up your OpenAI and Composio API keys
  • Install the required dependencies for Autogen and Composio
  • Initialize Composio and create a Tool Router session for Vapi
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Vapi tools
  • Run a live chat loop where you ask the agent to perform Vapi operations

What is AutoGen?

Autogen is a framework for building multi-agent conversational AI systems from Microsoft. It enables you to create agents that can collaborate, use tools, and maintain complex workflows.

Key features include:

  • Multi-Agent Systems: Build collaborative agent workflows
  • MCP Workbench: Native support for Model Context Protocol tools
  • Streaming HTTP: Connect to external services through streamable HTTP
  • AssistantAgent: Pre-built agent class for tool-using assistants

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.

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

What is Composio SDK?

Composio's Composio SDK 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 Composio SDK

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

How the Composio SDK works

The Composio SDK 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

Step by step08 STEPS
1

Prerequisites

You will need:

  • A Composio API key
  • An OpenAI API key (used by Autogen's OpenAIChatCompletionClient)
  • A Vapi account you can connect to Composio
  • Some basic familiarity with Autogen and Python async
2

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
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio python-dotenv
pip install autogen-agentchat autogen-ext-openai autogen-ext-tools

Install Composio, Autogen extensions, and dotenv.

What's happening:

  • composio connects your agent to Vapi via MCP
  • autogen-agentchat provides the AssistantAgent class
  • autogen-ext-openai provides the OpenAI model client
  • autogen-ext-tools provides MCP workbench support

4

Set up environment variables

bash
COMPOSIO_API_KEY=your-composio-api-key
OPENAI_API_KEY=your-openai-api-key
USER_ID=your-user-identifier@example.com

Create a .env file in your project folder.

What's happening:

  • COMPOSIO_API_KEY is required to talk to Composio
  • OPENAI_API_KEY is used by Autogen's OpenAI client
  • USER_ID is how Composio identifies which user's Vapi connections to use
5

Import dependencies and create Tool Router session

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Vapi session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["vapi"]
    )
    url = session.mcp.url
What's happening:
  • load_dotenv() reads your .env file
  • Composio(api_key=...) initializes the SDK
  • create(...) creates a Tool Router session that exposes Vapi tools
  • session.mcp.url is the MCP endpoint that Autogen will connect to
6

Configure MCP parameters for Autogen

python
# Configure MCP server parameters for Streamable HTTP
server_params = StreamableHttpServerParams(
    url=url,
    timeout=30.0,
    sse_read_timeout=300.0,
    terminate_on_close=True,
    headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
)

Autogen expects parameters describing how to talk to the MCP server. That is what StreamableHttpServerParams is for.

What's happening:

  • url points to the Tool Router MCP endpoint from Composio
  • timeout is the HTTP timeout for requests
  • sse_read_timeout controls how long to wait when streaming responses
  • terminate_on_close=True cleans up the MCP server process when the workbench is closed
7

Create the model client and agent

python
# Create model client
model_client = OpenAIChatCompletionClient(
    model="gpt-5",
    api_key=os.getenv("OPENAI_API_KEY")
)

# Use McpWorkbench as context manager
async with McpWorkbench(server_params) as workbench:
    # Create Vapi assistant agent with MCP tools
    agent = AssistantAgent(
        name="vapi_assistant",
        description="An AI assistant that helps with Vapi operations.",
        model_client=model_client,
        workbench=workbench,
        model_client_stream=True,
        max_tool_iterations=10
    )

What's happening:

  • OpenAIChatCompletionClient wraps the OpenAI model for Autogen
  • McpWorkbench connects the agent to the MCP tools
  • AssistantAgent is configured with the Vapi tools from the workbench
8

Run the interactive chat loop

python
print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
print("Ask any Vapi related question or task to the agent.\n")

# Conversation loop
while True:
    user_input = input("You: ").strip()

    if user_input.lower() in ["exit", "quit", "bye"]:
        print("\nGoodbye!")
        break

    if not user_input:
        continue

    print("\nAgent is thinking...\n")

    # Run the agent with streaming
    try:
        response_text = ""
        async for message in agent.run_stream(task=user_input):
            if hasattr(message, "content") and message.content:
                response_text = message.content

        # Print the final response
        if response_text:
            print(f"Agent: {response_text}\n")
        else:
            print("Agent: I encountered an issue processing your request.\n")

    except Exception as e:
        print(f"Agent: Sorry, I encountered an error: {str(e)}\n")
What's happening:
  • The script prompts you in a loop with You:
  • Autogen passes your input to the model, which decides which Vapi tools to call via MCP
  • agent.run_stream(...) yields streaming messages as the agent thinks and calls tools
  • Typing exit, quit, or bye ends the loop

Complete Code

Here's the complete code to get you started with Vapi and AutoGen:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

load_dotenv()

async def main():
    # Initialize Composio and create a Vapi session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["vapi"]
    )
    url = session.mcp.url

    # Configure MCP server parameters for Streamable HTTP
    server_params = StreamableHttpServerParams(
        url=url,
        timeout=30.0,
        sse_read_timeout=300.0,
        terminate_on_close=True,
        headers={"x-api-key": os.getenv("COMPOSIO_API_KEY")}
    )

    # Create model client
    model_client = OpenAIChatCompletionClient(
        model="gpt-5",
        api_key=os.getenv("OPENAI_API_KEY")
    )

    # Use McpWorkbench as context manager
    async with McpWorkbench(server_params) as workbench:
        # Create Vapi assistant agent with MCP tools
        agent = AssistantAgent(
            name="vapi_assistant",
            description="An AI assistant that helps with Vapi operations.",
            model_client=model_client,
            workbench=workbench,
            model_client_stream=True,
            max_tool_iterations=10
        )

        print("Chat started! Type 'exit' or 'quit' to end the conversation.\n")
        print("Ask any Vapi related question or task to the agent.\n")

        # Conversation loop
        while True:
            user_input = input("You: ").strip()

            if user_input.lower() in ['exit', 'quit', 'bye']:
                print("\nGoodbye!")
                break

            if not user_input:
                continue

            print("\nAgent is thinking...\n")

            # Run the agent with streaming
            try:
                response_text = ""
                async for message in agent.run_stream(task=user_input):
                    if hasattr(message, 'content') and message.content:
                        response_text = message.content

                # Print the final response
                if response_text:
                    print(f"Agent: {response_text}\n")
                else:
                    print("Agent: I encountered an issue processing your request.\n")

            except Exception as e:
                print(f"Agent: Sorry, I encountered an error: {str(e)}\n")

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You now have an Autogen assistant wired into Vapi through Composio's Tool Router and MCP. From here you can:
  • Add more toolkits to the toolkits list, for example notion or hubspot
  • Refine the agent description to point it at specific workflows
  • Wrap this script behind a UI, Slack bot, or internal tool
Once the pattern is clear for Vapi, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

Every Vapi action and event your agent gets out of the box.

Update Assistant

Tool to update an existing Vapi assistant configuration.

List Calls

Tool to list calls from Vapi.

Delete Chat

Tool to delete a chat by its ID from Vapi.

Get Chat

Tool to fetch chat details by ID.

Create Analytics Queries

Tool to create and execute analytics queries on VAPI data.

Create Assistant

Tool to create a new Vapi assistant with specified transcriber, voice, and AI model configurations.

Create Eval

Tool to create an eval for testing conversation flows.

Create OpenAI Chat

Tool to create an OpenAI-compatible chat using the Vapi API.

Create Phone Number

Tool to create a phone number with Vapi.

Create Monitoring Policy

Tool to create a monitoring policy in VAPI.

Create Provider Resource

Tool to create an 11Labs pronunciation dictionary resource.

Create Scorecard

Tool to create a scorecard for observability and evaluation.

Delete Call

Tool to delete a call by its unique identifier.

Delete Eval

Tool to delete an eval by ID.

Delete Phone Number

Tool to delete a phone number from Vapi.

Get Eval

Tool to retrieve an eval by its ID.

Delete Eval Run

Tool to delete an eval run by its ID from Vapi.

Update Eval

Tool to update an existing eval in Vapi.

Get Assistant

Tool to retrieve a specific assistant by ID from Vapi.

Get Call

Tool to fetch call details by ID.

Get File

Tool to retrieve a file by its ID from Vapi.

Get Insights

Tool to retrieve insights from Vapi.

List Monitoring Policies

Tool to retrieve monitoring policies from Vapi.

Get Observability Scorecard

Tool to list observability scorecards with optional filtering and pagination.

List Provider Resources

Tool to list provider resources from Vapi.

List Structured Outputs

Tool to list structured outputs with optional filtering.

Get Insights

Tool to retrieve insights from VAPI.

List Assistants

Tool to list all assistants in your VAPI organization.

List Chats

Tool to retrieve a list of chat conversations from VAPI.

List Evals

Tool to retrieve a paginated list of evals from Vapi.

List Provider Resources

Tool to retrieve provider resources from Vapi (e.

Update Insight

Tool to update an existing insight configuration in VAPI.

Create Phone Number

Tool to create a phone number with VAPI.

List Scorecards

Tool to retrieve a paginated list of scorecards from Vapi.

Create Session

Tool to create a new session in Vapi.

List Sessions

Tool to retrieve a paginated list of sessions from VAPI.

List Structured Outputs

Tool to list structured outputs with optional filtering and pagination.

Get Tool

Tool to fetch tool details by ID.

Test Code Tool Execution

Tool to test TypeScript code execution in Vapi's code tool environment.

Update Tool

Tool to update an existing Vapi tool configuration.

Update Phone Number

Tool to update an existing phone number configuration in VAPI.

Upload File

Tool to upload a file to Vapi Knowledge Base.

FAQ

Frequently asked questions

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.

Yes, you can. Autogen 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.

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.

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.

Start with Vapi.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Vapi tool your agent needs.Free to start.

Start building