How to Use the Descript MCP in Cursor

Q: Can Cursor automatically transcribe new Descript files?

Your agent can write the code to do this by calling createtranscription during development. It tests the transcription flow live so you know your webhook logic actually works.

Q: Does the Descript integration support team drives?

It certainly does. The listdrives tool exposes every workspace your account can access. Cursor reads that list to help you hardcode or configure the right environment variables for your MCP setup.

Pull live Descript transcripts and project data into your codebase using Cursor Agent mode.

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 Cursor

Create your Vinkius account to connect Descript to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Code with real transcripts

Stop mocking up fake dialogue for your media app features using your configured MCP Server. Cursor calls `get_transcription` to inject actual text from your video files straight into the editor. The agent processes the raw output and formats it into your chosen data structure. You build your parsing logic around real, messy human speech instead of clean test strings.

Query Descript projects natively

Building a dashboard for your video team requires constant context switching. This MCP integration lets you ask Cursor to `list_projects` and it writes the frontend components using live metadata. When you need to drill down into specific workspaces, `list_drives` pulls the exact IDs you need. Your agent writes the API calls while looking at the actual source of truth.

Trigger exports via MCP Server

Writing automation scripts for video rendering is incredibly tedious. You tell the agent to `create_export` and it tests the actual command against your live account. Once the render starts, Cursor can build polling functions by checking `list_exports`. You get working, tested code that handles the entire media pipeline without leaving your IDE.

Setup guide

Set up Descript MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Descript MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Descript transactions." If the MCP tools are loaded correctly, Cursor will call the Descript tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "descript-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Create an mcp.json file in your project root directory. Add the Descript server command or remote URL under the tools configuration. Toggle Agent mode on in your chat panel to start.

Your agent can write the code to do this by calling create_transcription during development. It tests the transcription flow live so you know your webhook logic actually works.

You build internal tools ten times faster when the AI can see your live data. Calling get_project directly in the editor means your agent generates accurate types and interfaces instantly.

It certainly does. The list_drives tool exposes every workspace your account can access. Cursor reads that list to help you hardcode or configure the right environment variables for your MCP setup.

Your credentials live strictly inside your local environment or the Vinkius managed endpoint. The raw text and video metadata only exist in memory while the agent builds your code. The sandbox destroys the context window after execution.

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