How to Use the AssemblyAI MCP in AutoGen

Q: How do I add AssemblyAI MCP tools to my AutoGen agents?

Install autogen-extmcp. Initialize mcpservertools with your Vinkius HTTP endpoint, and pass the resulting tools array directly to your AssistantAgent.

Q: How does AutoGen handle AssemblyAI transcription delays?

The executing agent submits the file using transcribeaudiourl and informs the group chat that it is waiting. Other agents can pause or work on different tasks until the text is ready.

Give your AutoGen agents the ability to transcribe, debate, and analyze audio files using the AssemblyAI MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AssemblyAI MCP to AutoGen

Create your Vinkius account to connect AssemblyAI to AutoGen 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 AssemblyAI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Audio Analysis

Your AutoGen group chat analyzes meeting recordings autonomously. One agent executes `transcribe_audio_url` via the MCP integration and grabs the text. A second agent pulls `get_sentiments` to evaluate the room's mood. They discuss the findings in real time. If the sentiment agent flags a hostile exchange, a third compliance agent steps in. It requests `get_speakers` to identify who caused the issue. The group debates the severity of the interaction before generating a final consensus report.

AssemblyAI MCP Server Debates

Summarization tools let your agents debate audio context. A summarizer agent might use `get_summary` to draft a quick recap. Another detail-oriented agent then challenges that recap by analyzing the raw `get_transcript` output, pointing out missed nuances. They negotiate the final output. You aren't just running a script; you're watching specialized AI roles argue over the exact meaning and context of spoken words until they reach a mathematically sound agreement.

Autonomous Transcript Management

Workspace management tools let your agents clean up old audio files. An admin agent monitors the queue using `list_transcripts`. When a job finishes and the data is extracted via `get_chapters` and `get_topics`, the admin decides if the file is still needed. If the debate is over, the admin calls `delete_transcript` to purge the record. The agents handle the entire lifecycle of the audio file without human intervention.

Setup guide

Set up AssemblyAI MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes AssemblyAI tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="AssemblyAI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent AssemblyAI data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

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

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="AssemblyAI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent AssemblyAI data")
    print(result.messages[-1].content)

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 AssemblyAI. 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 AssemblyAI 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 AssemblyAI MCP in AutoGen

Install `autogen-ext[mcp]`. Initialize `mcp_server_tools` with your Vinkius HTTP endpoint, and pass the resulting tools array directly to your `AssistantAgent`.

Yes. Any agent in the group chat equipped with the tool adapter can call `get_topics` or `get_speakers` to support their specific argument.

The executing agent submits the file using `transcribe_audio_url` and informs the group chat that it is waiting. Other agents can pause or work on different tasks until the text is ready.

The agent reports the error back to the chat. Another agent can suggest retrying the call or using `get_chapters` to break the data into smaller, readable pieces.

Vinkius isolates your MCP session in a secure V8 sandbox. The raw audio URLs and extracted speaker labels exist only during the active tool call and vanish the second the connection drops.

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

Vercel AI SDK sdk-typescript