How to Use the Descript MCP in AutoGen

Q: How do I register Descript tools with an AutoGen AssistantAgent?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP URL. Pass the resulting tool list directly into your AssistantAgent constructor to give it access to video editing tools.

Q: Can AutoGen handle multiple Descript drives simultaneously?

Yes, the agents can query listdrives to see all accessible workspaces. They coordinate which files go where by discussing the drive structure in their conversation log.

Let AutoGen agents debate and coordinate Descript transcription and export tasks automatically.

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 AutoGen

Create your Vinkius account to connect Descript 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 Descript with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Descript MCP Server Tasks via Multi-Agent Debate

The Descript MCP Server gives your AutoGen agents the ability to manage complex rendering pipelines through consensus. An editor agent can request an export via `create_export`, while a quality agent verifies the project details first. By checking `list_exports`, the agents track the rendering progress together and decide when to notify your team. This multi-agent setup prevents broken or incomplete videos from being exported without consensus.

Collaborative Audio Transcription Workflows

Your AutoGen team uses `create_transcription` over MCP to convert raw video files into text drafts. A specialized transcription agent handles the initial API call, while a reviewer agent checks the output using `get_transcription`. If the text contains errors, the reviewer agent can flag the project by querying `get_project` to check the source file. The agents discuss corrections in their chat loop before finalizing the transcript.

Automated Workspace Setup and Template Auditing

AutoGen agents can audit your team layouts by calling `list_templates` and comparing them against production guidelines. A design agent and a project manager agent debate which template matches the current campaign. Once they agree, they use `list_drives` to locate the correct storage directory and prepare the workspace. This process ensures your video projects are organized consistently across all team drives.

Setup guide

Set up Descript 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 Descript 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="Descript_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Descript 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="Descript_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Descript 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 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 AutoGen

The agents chat using their built-in debate loop, querying get_project to check the current state. They only trigger actions like create_export once all agents agree the video is ready.

Install autogen-ext[mcp] and use mcp_server_tools with your Vinkius HTTP URL. Pass the resulting tool list directly into your AssistantAgent constructor to give it access to video editing tools.

Yes, the agents can query list_drives to see all accessible workspaces. They coordinate which files go where by discussing the drive structure in their conversation log.

Yes, the McpToolAdapter handles schema conversion automatically for both transport methods. You can run your agents locally or deploy them to cloud environments using Vinkius's hosted MCP endpoints.

Your media transcripts and project details are executed within Vinkius's secure, ephemeral V8 isolate sandbox. No data is stored, and the zero-trust architecture ensures that only authorized agents can access your files.

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