Descript MCP. Manage video assets and transcripts via chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Descript MCP Server lets your AI agent manage video and podcast production without ever opening the editor. You can list projects, pull full transcripts for blog posts, check export statuses, and organize media assets conversationally.
It turns your video workflow into a series of simple chat commands.
What your AI agents can do
Create export
Starts a media export job for a specific project.
Create transcription
Sends a media file to generate a full text transcription.
Get project
Retrieves detailed information about a single Descript project.
Retrieves metadata for any Descript project, including composition details and associated files.
Navigates and lists all team drives and project folders within your Descript account.
Retrieves a comprehensive list of all active and archived Descript projects.
Processes a media file (audio or video) and returns a full, time-stamped transcription.
Retrieves the final, processed text and speaker metadata for a previously requested transcription.
Checks and lists the status of all scheduled and completed media exports.
Initiates an export job for a specified Descript project, setting the target format and resolution.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Descript MCP Server: 8 Tools for Media & Export Ops
Use these tools to manage your entire Descript content pipeline—from listing projects to exporting final media and extracting full transcripts.
019d7584create export
Starts a media export job for a specific project.
019d7584create transcription
Sends a media file to generate a full text transcription.
019d7584get project
Retrieves detailed information about a single Descript project.
019d7584get transcription
Pulls the final, processed text result from a transcription job.
019d7584list drives
Shows a list of all team drives available in your Descript account.
019d7584list exports
Lists all export jobs and their current status.
019d7584list projects
Lists every project you have saved in Descript.
019d7584list templates
Retrieves a list of available Descript templates.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Descript, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Your AI agent lets you run your whole video and podcast workflow through chat. You don't even have to open the editor. You can list all your projects, pull full transcripts for blog posts, check export statuses, and organize media assets just by chatting with it. It turns your video workflow into a bunch of simple chat commands.
Project Management
list_projects lets you see every Descript project you've saved. You can then use get_project to pull detailed info on any single project, including its composition details and associated files. You can also list_drives to see all the team drives and project folders in your Descript account.
Transcripts and Text
create_transcription sends any media file—audio or video—to generate a full, time-stamped transcription. When that's done, you use get_transcription to pull the final, processed text and speaker metadata for the job.
Exports and Media
list_exports lets you check the status of every scheduled and completed media export. If you're ready to send it out, you kick things off with create_export, which starts a media export job for a specific project, letting you set the target format and resolution. Finally, you can create_export to start a media export job for a specific project.
How Descript MCP Works
- 1 Subscribe to the Descript integration on the Vinkius Marketplace.
- 2 Generate an API token from your Descript account (Settings → API tokens → Create token).
- 3 Ask your AI agent to run a command, like 'List all projects' or 'Transcribe this video,' using the available tools.
The bottom line is, your AI agent handles the authentication and API calls, letting you manage complex media pipelines using natural language.
Who Is Descript MCP For?
Content creators, podcast producers, and marketing teams need this. If your job involves taking video recordings and turning them into multiple formats—show notes, blog posts, social media clips—you're hitting a wall. You're spending too much time copying, pasting, and jumping between different apps. This tool lets you manage the whole process from a single chat interface.
Uses the agent to pull full transcripts from a video project, then asks it to format the text for a blog post draft.
Runs list_projects to find an episode, then uses create_transcription to pull the full transcript for show notes and SEO optimization.
Checks list_exports to confirm if a key asset is ready, and then uses get_project to grab the final media link for a campaign.
What Changes When You Connect
- Manage projects and assets without opening Descript. You use the agent to run
list_projectsandget_projectto see all metadata, then ask for the specific transcript or file link. - Streamline content repurposing. Instead of manually copying transcripts, you ask the agent to
create_transcriptionon a media file, and thenget_transcriptionpulls the full text for blog posts or show notes. - Control your media exports. Use
list_exportsto check if a video is ready, and then the agent can usecreate_exportto start the job, giving you a direct download link when done. - Navigate your content library. Use
list_drivesto see the main team folders, and thenlist_projectsto drill down into specific compositions and recordings. - Audit your content status. You can check the status of old jobs by running
list_exports, ensuring you know exactly which assets are finished and which are still processing. - Access core project data. With
get_project, you pull all the raw project data—compositions, media files, and transcripts—all in one API call.
Real-World Use Cases
Podcast Show Note Generation
A producer finishes an episode and needs show notes immediately. Instead of downloading the video, opening the transcript, and copy-pasting, they just ask their agent: 'Get the full transcript for Episode 47.' The agent uses create_transcription and then get_transcription to give the clean, timed text needed for SEO.
Multi-Platform Content Audit
A marketing team needs to know every video project they've worked on this quarter. They ask the agent to run list_projects. The agent returns a list of 50 titles and their last modified date, letting the team quickly audit the entire content library.
Video Asset Retrieval
A client needs the final, high-res version of the 'Q1 Demo' video. They ask the agent to check the status using list_exports. Once the status is 'complete,' the agent uses get_project to retrieve the direct download link for the final MP4.
Finding Old Recordings
The team needs a specific recording from last year's meeting, but doesn't know which drive it's in. They ask the agent to run list_drives, narrow it down, and then use list_projects to find the exact recording within that drive.
The Tradeoffs
Manual API Chaining
Writing a script that calls list_projects, then loops through the results to call get_project for every single one, and then handles the data aggregation in Python.
→
Don't write the loop. Just tell your agent: 'List the three most recent projects and get their transcripts.' The agent orchestrates the necessary calls (list_projects and get_transcription) for you, minimizing code.
Assuming Export Readiness
Calling get_project and assuming the video export is ready, only to find the status is 'pending' and the call fails or returns stale data.
→
Always check the export status first. Run list_exports to confirm the job is complete. Only then should you proceed to use get_project or attempt to retrieve the asset.
Ignoring Transcripts
Downloading a video just to copy the spoken words, which is tedious and prone to error.
→
Use the agent to run create_transcription on the video. This gives you a clean, structured text file with timestamps, which is better for repurposing.
When It Fits, When It Doesn't
Use this if your workflow requires managing content assets across multiple stages: discovery (finding projects via list_projects), content extraction (getting transcripts via create_transcription), and final distribution (checking exports with list_exports). This is for the full content lifecycle. Don't use this if you only need to check one single piece of metadata; in that case, just use get_project directly. You won't need to use list_drives unless you are genuinely lost in the folder structure and need to find the right container first.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Sifting through video assets shouldn't require a dozen manual steps.
Today, if you need a project overview, you jump into Descript. You click 'Projects,' then you click the specific composition. You have to drill down to find the transcript, then you might have to open a separate 'Exports' tab just to check if the video is done. It's a dozen clicks, a dozen tabs, and half the time, you're just copying and pasting text into a document.
With this MCP server, you just talk to your agent. You ask it, 'What projects are ready for export?' The agent runs `list_projects` and `list_exports`, pulling the status and titles directly into the chat. You get the full picture without touching the video editor.
Descript MCP Server: Manage transcripts and exports via chat.
You no longer need to manually export a video, wait for the file, and then upload it to a separate service just to get the text. You simply ask the agent to `create_transcription` on the source media. The agent handles the API call and returns the full text result instantly.
It cuts out the entire manual process. You start with the media, and the system gives you the structured text you need for blogs or social media. It's just that simple.
Common Questions About Descript MCP
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.
How do I use the `list_drives` tool to check my team's project scope? +
The list_drives tool immediately shows you all available team drives. This lets your agent navigate the entire organization's project space, not just your personal folders.
What happens if the `create_export` tool fails during a large project export? +
If an export fails, the tool returns a specific error code and the reason. You can then use get_project to check the status and attempt a retry.
Can my AI agent handle multiple media types when running `create_transcription`? +
Yes, the create_transcription tool supports both audio and video files. It extracts full text and timestamps regardless of the media format.
Does the `list_projects` tool handle projects that are archived or hidden? +
The list_projects tool lists all available Descript projects, including those marked as archived. You can then filter the results by status.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
EX.CO Video Experience
Equip your AI agent to manage video libraries, track interactive content, and monitor analytics via the EX.CO API.
RandomDuck
Brighten your day with random duck images, GIFs, and HTTP status ducks for developers.
Playground AI
Generate, inpaint, upscale, and transform images using Playground AI's powerful models via natural language.
You might also like
Socket.dev (Dependency Security)
Protect your software supply chain by scanning dependencies, checking package security scores, and monitoring threat feeds directly from your AI agent.
Cody AI
Enable your AI agent to manage knowledge-base bots, import documents, and query trained AI assistants via the Cody AI API.
CAMB.AI
Translate and dub audio content into dozens of languages using AI voices that sound natural and preserve speaker identity.