SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Rev ai MCP with Autogen

Connect Autogen to Rev ai MCP. Transcribe this meeting audio to text, get captions for latest video job, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Rev ai logoRev ai
Api Key

Rev ai is a speech recognition platform that converts audio and video into text using advanced machine learning. Perfect for fast, accurate transcriptions and unlocking searchable insights from your recordings.

11 Tools

Introduction

This guide walks you through connecting Rev ai to AutoGen using the Composio tool router. By the end, you'll have a working Rev ai agent that can submit transcription jobs, fetch transcripts and captions, transcribe live streams, and manage custom vocabularies through natural language commands.

This guide will help you understand how to give your AutoGen agent real control over a Rev ai account through Composio's Rev ai MCP server.

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

Also integrate Rev ai with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIPydantic AI

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 Rev ai
  • Wire that MCP URL into Autogen using McpWorkbench and StreamableHttpServerParams
  • Configure an Autogen AssistantAgent that can call Rev ai tools
  • Run a live chat loop where you ask the agent to perform Rev ai 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 Rev ai MCP server, and what's possible with it?

The Rev ai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Rev ai account. It provides structured and secure access to your speech-to-text workflows, so your agent can perform actions like transcribing audio, retrieving transcripts, managing custom vocabularies, and handling transcription jobs on your behalf.

  • Automated audio and video transcription: Effortlessly submit audio or video files for transcription, and let your agent monitor job progress until transcripts are ready.
  • Transcript and caption retrieval: Retrieve full transcripts in multiple formats or download caption files (SRT, VTT) for completed jobs—perfect for both review and publishing.
  • Custom vocabulary management: Enhance transcription accuracy by submitting and maintaining domain-specific vocabularies, including adding new terms and deleting unused sets.
  • Transcription job management: List, fetch, or delete transcription jobs by ID, making it easy for your agent to keep your workspace organized and up-to-date.
  • Real-time streaming transcription: Start live stream transcriptions for instant speech-to-text conversion, allowing your agent to process and react to spoken content in real time.

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 Rev ai 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 Rev ai 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 Rev ai 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 Rev ai session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["rev_ai"]
    )
    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 Rev ai 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 Rev ai assistant agent with MCP tools
    agent = AssistantAgent(
        name="rev_ai_assistant",
        description="An AI assistant that helps with Rev ai 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 Rev ai 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 Rev ai 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 Rev ai 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 Rev ai 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 Rev ai session
    composio = Composio(api_key=os.getenv("COMPOSIO_API_KEY"))
    session = composio.create(
        user_id=os.getenv("USER_ID"),
        toolkits=["rev_ai"]
    )
    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 Rev ai assistant agent with MCP tools
        agent = AssistantAgent(
            name="rev_ai_assistant",
            description="An AI assistant that helps with Rev ai 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 Rev ai 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 Rev ai 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 Rev ai, you can reuse the same structure for other MCP-enabled apps with minimal code changes.
TOOLS

Supported Tools

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

Delete Custom Vocabulary

Tool to delete a completed custom vocabulary and its data.

Delete Job By ID

Tool to delete a completed transcription job and its data.

Get Account

Tool to retrieve developer account details.

Get Captions

Tool to retrieve captions (SRT or VTT) for a completed Rev.

Get Custom Vocabulary Details

Tool to retrieve custom vocabulary processing details.

Get Job by ID

Tool to fetch details of a transcription job by its ID.

Get List of Jobs

Tool to get list of transcription jobs from the past 30 days.

Get Transcript by ID

Tool to retrieve the transcript of a completed Rev.

Start Stream Transcription

Constructs a WebSocket URL for a Rev.

Submit Custom Vocabulary

Tool to submit a custom vocabulary for improved speech recognition.

Submit Transcription Job

Tool to submit a new transcription job.

FRAMEWORKS

How to build Rev ai MCP Agent with another framework

Claude Code logo

Claude Code

Use Rev ai MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Rev ai MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Rev ai MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Rev ai MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Rev ai MCP with Grok Bot

Codex logo

Codex

Use Rev ai MCP with Codex

OpenClaw logo

OpenClaw

Use Rev ai MCP with OpenClaw

Hermes logo

Hermes

Use Rev ai MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Rev ai MCP with Atomic Agent

Google ADK logo

Google ADK

Use Rev ai MCP with Google ADK

LangChain logo

LangChain

Use Rev ai MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Rev ai MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Rev ai MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Rev ai MCP with LlamaIndex

CrewAI logo

CrewAI

Use Rev ai MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Rev ai MCP with Pydantic AI

FAQ

Frequently asked questions

With a standalone Rev ai MCP server, the agents and LLMs can only access a fixed set of Rev ai tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Rev ai 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 Rev ai tools.

Yes, absolutely. You can configure which Rev ai 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 Rev ai data and credentials are handled as safely as possible.

Start with Rev ai.It takes 30 seconds.

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

Start building