How to Use the Descript MCP in Claude

Q: How do I install the Descript MCP Server in Claude Desktop?

Open your developer settings and edit the claudedesktopconfig.json file. Add the Descript server details under the mcpServers key, then restart the app completely. You will see a hammer icon when the tools load.

Q: Can Claude Desktop read my Descript transcripts directly?

Yes. The agent uses the gettranscription tool to pull text straight from your video files. You never have to copy and paste from the web dashboard again.

Q: What happens when I ask Claude Desktop to export a Descript project?

The agent fires off a createexport command to the rendering engine. You can then monitor the job status by asking it to run listexports.

Get Descript transcripts and manage video projects right inside Claude Desktop without opening the editor.

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 Claude Desktop

Create your Vinkius account to connect Descript to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Transcribe media fast

Drop an audio file into your chat and tell your MCP Server to run `create_transcription`. Your agent processes the raw file and pulls the text back into the conversation for immediate review. You skip the manual upload steps entirely. Once the job finishes, `get_transcription` grabs the exact dialogue so you can draft show notes or blog posts on the spot.

Control your Descript MCP Server

Managing video files usually means digging through endless folders. Now you ask your agent to `list_projects` and find exactly what your team is working on. If you need specific assets, `list_drives` points you to the right workspace. You get full visibility into your video pipeline directly from the Claude interface.

Export and format

Getting a finished cut out via this MCP integration takes seconds. Just trigger `create_export` and your agent handles the rendering request in the background. Need a consistent look for a new series? Have Claude check `list_templates` to grab the right layout before you start cutting. You track the progress later using `list_exports`.

Setup guide

Set up Descript MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Descript MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Descript MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under descript-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 Claude Desktop

Open your developer settings and edit the claude_desktop_config.json file. Add the Descript server details under the mcpServers key, then restart the app completely. You will see a hammer icon when the tools load.

Yes. The agent uses the get_transcription tool to pull text straight from your video files. You never have to copy and paste from the web dashboard again.

It sure does. Go to your integration settings on claude.ai and add a custom connector. Paste the remote URL for the server and authenticate to start querying your video projects.

The agent fires off a create_export command to the rendering engine. You can then monitor the job status by asking it to run list_exports.

Vinkius handles authentication through a zero-trust V8 Isolate sandbox. Your raw media files and raw transcripts pass through ephemeral sessions that disappear the moment your query finishes. Nothing gets stored permanently.

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