Descript Connector for AI agents.
8 live capabilities
Manage podcast transcripts and video exports through a conversational interface.
Waiting for input…
Why people use Descript
Descript for Automated Podcast Content Repurposing
This Connector lets your agent do the heavy lifting. You can just ask for the transcript of a specific project and have your agent grab the text for you. It turns a 20-minute manual task into a 5-second request.
What Vinkius changes
That you get a conversational interface for your entire Descript media library.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Turning a podcast into a blog post
A podcaster needs to turn a 2-hour interview into a blog post.
- Real-world use case 02
Checking if a video is ready
A video editor wants to know if the 'Q1 Demo' is done.
- Real-world use case 03
Finding social media assets
A social media manager needs to find all projects related to 'Summer Sale.
Complete set · 8capabilities
The complete Descript capability set.
These are the exact actions your AI can choose when you ask it to work with Descript.
01—04
4 capabilities in this set.
Part of 8 available through Descript.
- 01 Capability
List exports
See a list of all your project exports. You can use this to monitor which files are still rendering.
- 02 Capability
List templates
See what project templates are currently available. This helps you identify the best starting point for a new video.
- 03 Capability
List projects
See every project in your Descript account at once. This helps you keep track of what's in progress without manual browsing.
- 04 Capability
Get project
Pull specific details about a single project. Use this to check metadata or specific project settings quickly.
05—08
4 capabilities in this set.
Part of 8 available through Descript.
- 05 Capability
List drives
View all team drives available to you. This makes it easier to navigate shared assets across a larger production team.
- 06 Capability
Create transcription
Send an audio or video file to be transcribed. This starts the process of turning raw media into usable text.
- 07 Capability
Get transcription
Fetch the text result from a previous transcription. Use this to grab the content for blog posts or subtitles.
- 08 Capability
Create export
Start the export process for a project. This triggers the rendering of your final video or audio file.
Set up in minutes
One URL. Then ask Descript to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Descript from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_8eagsgAxE9fz07ak7MnGFQnckwrN3tQYzrVI8IIB/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Descript, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Descript for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_8eagsgAxE9fz07ak7MnGFQnckwrN3tQYzrVI8IIB/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Descript URL.
- Step 03
Save and start
Save the connection and enable Descript in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"descript": {
"url": "https://edge.vinkius.com/vk_preview_8eagsgAxE9fz07ak7MnGFQnckwrN3tQYzrVI8IIB/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Descript
Open Agent mode in chat and ask: "Using Descript, help me...". 8 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"descript": {
"url": "https://edge.vinkius.com/vk_preview_8eagsgAxE9fz07ak7MnGFQnckwrN3tQYzrVI8IIB/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Descript
Ask Copilot: "Using Descript, help me...". 8 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"descript": {
"url": "https://edge.vinkius.com/vk_preview_8eagsgAxE9fz07ak7MnGFQnckwrN3tQYzrVI8IIB/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Descript
Open Cascade and ask: "Using Descript, help me...". 8 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"descript": {
"url": "https://edge.vinkius.com/vk_preview_8eagsgAxE9fz07ak7MnGFQnckwrN3tQYzrVI8IIB/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Descript
Ask Cline: "Using Descript, help me...". 8 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add descript --transport http "https://edge.vinkius.com/vk_preview_8eagsgAxE9fz07ak7MnGFQnckwrN3tQYzrVI8IIB/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Descript
Ask Claude: "Using Descript, show me...". 8 tools are ready
Where the request belongs
Work Descript can move forward.
This is for content creators and media producers who are tired of manual data entry. It solves the headache of hunting for files and copy-pasting transcripts across multiple platforms.
Content Creator
Repurposing a 60-minute video into 10 tweets by asking the agent to pull the transcript for the latest episode.
Podcast Producer
Finding the best takes in a drive and getting the download links for the final edit on a Tuesday afternoon.
Marketing Manager
Checking the status of 20 different video exports at once to see what's ready for the social team.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors3Scribe
Automated audio and video transcription. create jobs, monitor progress, and retrieve text via AI.
Castmagic
Automate audio and video content repurposing via Castmagic. generate transcripts, show notes, and social posts directly from any AI agent.
ContentGroove
Equip your AI agent to automatically generate video highlights, splice long-form clips, and manage video projects natively with ContentGroove.
Verbit
Automate professional transcription and captioning via Verbit. upload media, track job progress, and retrieve transcripts in multiple formats directly from your AI agent.
Sonix
Automate transcription, translation, and media management via Sonix. transcribe audio/video, generate subtitles, and create AI summaries directly from any AI agent.
Rev.com
Automate human-powered transcription via Rev.com. manage orders, captions, and file metadata with AI.
Bring your own AI
Change the model, client or framework. Keep Descript connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Descript.
The practical details behind the request, access and result.
Can the Descript MCP actually edit my videos?
No, this Connector is for managing your projects, pulling transcripts, and checking exports. You still need the Descript app for actual editing tasks like cutting or adding effects.
How do I get my transcripts into a blog post?
You can ask your agent to pull the transcription from a specific project. Once the agent has the text, you can then ask it to rewrite that text into a blog post format.
Can I use the Descript MCP to manage my team's files?
Yes, you can use list_drives to navigate and find specific recordings or compositions across your team's shared drives.
Does this Connector work with my existing Descript account?
Yes, it connects directly to your account using an API token. You'll just need to create that token in your Descript settings first.
How many projects can I list at once?
You can list all the projects in your account. This is great for getting a high-level view of your entire production pipeline in one go.
Can I check if my video is finished rendering?
Yes, you can use the list_exports capability to see the status of all your exports and get download links for the ones that are ready.
Is there a limit to how many transcripts I can pull?
You can pull transcripts from any project in your Descript account. This makes it easy to repurpose content across multiple platforms quickly.
How do I get my Descript API token?
Log in to your Descript account at descript.com. Navigate to Settings (click your profile icon). In the left sidebar, select API tokens. Click the Create token button, give it a descriptive name, and select the specific Drive you want it associated with. Copy the token immediately. it will not be shown again after you close the window. Paste it into the configuration field below.
Can I convert a podcast transcript into a blog post automatically?
Yes. Ask your AI agent to pull the full transcript from a Descript project, then instruct it to reformat the content into a structured blog post. It retrieves speaker labels, timestamps, and the complete text. perfect for creating show notes, summaries, or full articles from your recordings.
What if I work across multiple Descript drives?
Each API token is tied to a specific Drive. If you work across multiple drives (e.g., separate drives for different shows or clients), generate a separate token for each drive and configure multiple integrations. Your AI agent can then query projects from any of your drives.
Is this useful for agencies producing video content for clients?
Absolutely. Agencies can use the AI agent to pull transcripts across client projects, track export statuses, and retrieve download links. all from a single conversational interface. No need to log in and out of different client workspaces or manually download files from the Descript dashboard.
One connection away
Give your agent a direct line to Descript.
Connect Descript once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available