How to Use the AssemblyAI MCP in OpenAI Agents SDK

Q: Can my OpenAI agent list all past AssemblyAI jobs?

Yes, the agent calls listtranscripts to pull your recent history. It can then filter or analyze past recordings without needing the original audio files.

Q: How does the OpenAI agent know when an AssemblyAI transcription finishes?

The agent polls the status using gettranscript. You can set up guardrails to ensure it waits for a completed status before trying to extract summaries.

Q: Does this setup support automatic summarization?

It sure does. The agent invokes getsummary on any completed job. You dictate the summary format in your system prompt.

Build production voice agents with OpenAI Agents SDK that transcribe and analyze audio using AssemblyAI.

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 OpenAI Agents SDK

Create your Vinkius account to connect AssemblyAI to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect this MCP Server to your OpenAI agent

Give your production agent system direct access to audio transcription through this MCP Server. You pass an audio link to `transcribe_audio_url`, and the agent handles the rest. OpenAI's built-in guardrails validate the inputs before the request ever hits the server. Once the job finishes, the agent pulls the text using `get_transcript`. You get full visibility into the execution via the OpenAI dashboard tracing. If an error occurs, the agent catches it instead of crashing your application.

Audio intelligence and topic mapping

Raw text rarely gives you the full picture of a conversation. Your agent can call `get_chapters` to segment a long podcast into logical sections. Handoffs make this powerful. One specialized agent handles the transcription, then passes the ID to an analysis agent. That second agent runs `get_topics` and `get_sentiments` to figure out what the speakers actually discussed. It maps out the emotional arc of the recording. You wire up complex voice analysis pipelines without writing custom API wrappers.

Speaker detection and cleanup

Knowing who said what matters just as much as the words themselves. The agent hits `get_speakers` to label different voices in a multi-person meeting. The tool converts a wall of text into a structured dialogue format. Managing storage is just as easy. You can configure your agent to call `delete_transcript` after processing the data. Your system stays clean, and you avoid storing sensitive recordings longer than necessary.

Setup guide

Set up AssemblyAI MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all AssemblyAI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives AssemblyAI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate AssemblyAI tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="AssemblyAI Agent",
            instructions="You have access to AssemblyAI tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Use the MCPServerStreamableHttp class with the Vinkius endpoint URL. Pass it in the mcp_servers array when constructing your agent. The SDK auto-discovers all the MCP tools immediately.

Yes, the agent calls `list_transcripts` to pull your recent history. It can then filter or analyze past recordings without needing the original audio files.

The agent polls the status using `get_transcript`. You can set up guardrails to ensure it waits for a completed status before trying to extract summaries.

It sure does. The agent invokes `get_summary` on any completed job. You dictate the summary format in your system prompt.

This MCP Server processes raw audio URLs and transcribed text. Vinkius isolates the execution in an ephemeral V8 sandbox, meaning your voice recordings and generated transcripts vanish from memory the moment the request ends. Zero persistent data gets left behind.

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