How to Use the Descript MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK run Descript transcripts automatically?

Yes, use the createtranscription tool to initiate the process. Your agent then waits for the result and pulls the data using gettranscription.

Connect your OpenAI Agents SDK to Descript to automate exports and handle project transcripts without manual clicks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Descript MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Descript projects with OpenAI Agents SDK

Your agent pulls project metadata using `get_project` or lists entire drive contents via `list_drives`. It keeps your production pipeline moving by checking statuses before triggering expensive compute tasks. Everything stays within your agent's execution context. You avoid manual context switching by letting the Python SDK handle project discovery through `list_projects` automatically.

Automate media processing for OpenAI Agents SDK

Feed raw files into `create_transcription` to get text back instantly. Your agent then uses `get_transcription` to parse output, allowing for automated content tagging or summary generation. This workflow bypasses the UI entirely. You script the entire lifecycle from raw upload to finished text asset.

Direct export control for OpenAI Agents SDK

Call `create_export` to push finished video or audio files directly to your storage bucket. You track progress by checking `list_exports` to see if your render finished successfully. This MCP server provides the hooks needed for complex media pipelines. It removes the need for human intervention in your production agent system.

Setup guide

Set up Descript 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 Descript tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the necessary dependencies and initialize the MCPServerStreamableHttp class. Pass the server instance into your agent's constructor to give it immediate access to all eight tools.

Yes, use the `create_transcription` tool to initiate the process. Your agent then waits for the result and pulls the data using `get_transcription`.

It is built for production environments. The server handles the heavy lifting while your agent maintains full control over project state and file handling.

Files remain within your account infrastructure. The server only transmits the instructions and metadata required to perform the requested actions.

Vinkius uses ephemeral isolated sandboxes for every session. We only process project transcripts and export logs, ensuring your sensitive media assets stay locked down.

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