How to Use the Maestra MCP in OpenAI Agents SDK

Q: How do I connect the OpenAI Agents SDK to Maestra?

Just pip install openai-agents and instantiate MCPServerStreamableHttp with your Vinkius endpoint URL. Pass it to your Agent constructor in the mcpservers list and set cacheToolsList=True for better performance.

Q: Can my OpenAI agent choose different voices with Maestra?

Yes. The agent calls the listavailableaivoices tool to get a list of all options. Then, it uses the generateaivoiceover tool with the file ID and chosen voice ID.

Automate your global video localization pipeline with the OpenAI Agents SDK and Maestra's API.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Maestra MCP to OpenAI Agents SDK

Create your Vinkius account to connect Maestra 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 Maestra with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Production Localization Agent

This isn't for prototypes. Connect your OpenAI Agent to this MCP Server and build a localization pipeline that actually works. Your agent can `upload_media_for_transcription`, check its status with `get_file_details`, and then automatically `translate_transcription` into multiple languages. The OpenAI SDK's built-in guardrails mean you can hand off tasks between agents—one for uploads, another for voiceovers—with full tracing. You see every API call, every decision. It's how you scale localization without losing control.

Generate Voiceovers on Demand

Let your agent choose the right voice for the job. It can query all available options using `list_available_ai_voices` and then trigger voiceover generation for a specific file with `generate_ai_voiceover`. Because you're using the OpenAI Agents SDK, you can build safety checks around this. For example, require human approval before generating a voiceover for a high-value video, all tracked in your OpenAI dashboard.

Manage Your Media Library via Agent

Your agent gets full visibility into your Maestra account. It can organize work with `list_account_folders` and see every processed file using `list_maestra_files`. No more manual checking in a web UI. Once a job is done, the agent uses `export_transcription_results` to get a download link for the final SRT or VTT file. This closes the loop, letting you pull completed assets directly into your CMS or storage bucket.

Setup guide

Set up Maestra 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 Maestra tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Maestra 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="Maestra Agent",
            instructions="You have access to Maestra 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 Maestra. 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 Maestra 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 Maestra MCP in OpenAI Agents SDK

Just `pip install openai-agents` and instantiate `MCPServerStreamableHttp` with your Vinkius endpoint URL. Pass it to your Agent constructor in the `mcp_servers` list and set `cacheToolsList=True` for better performance.

Yes. The agent calls the `list_available_ai_voices` tool to get a list of all options. Then, it uses the `generate_ai_voiceover` tool with the file ID and chosen voice ID.

The SDK provides tracing for every tool call. If the Maestra API returns an error, it's captured in the agent's run history, which you can inspect in the OpenAI dashboard for debugging.

Yes. While the SDK auto-discovers all tools, you can build custom guardrails or logic within your agent to restrict its actions, for instance, by only allowing it to call read-only tools like `get_file_details`.

The server handles the audio and video files you provide via the `upload_media_for_transcription` tool. Vinkius processes these files in an ephemeral, zero-trust sandbox, and your Vinkius endpoint token handles all authentication, keeping your API keys secure.

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