Descript integration
Audio and video editing platform with AI-powered transcription and editing. The API enables importing media files, creating AI-driven edits via natural language prompts, managing async jobs, retrieving published project metadata, and partner integrations for media transfer into Descript.
Say what should happen.
The workflow builds itself.
Common Descript use cases
- Browse all projects in a Descript drive
- Inspect project contents before publishing
- Retrieve metadata for a shared Descript project
- Monitor status of recent import and editing jobs
- Publish a finished video project as a shareable link
- Poll for import job completion after submitting media
- Create Edit in Descript button for partner application
- Cancel an import job that was started with incorrect files
- Import interview recordings into Descript for transcription
- Remove filler words from a recorded interview automatically
What you can do with Descript
Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.
Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.
Job, 5 operations
agent_editAgent editPOSTSubmits an AI agent job to create or edit a Descript project using a natural language prompt.cancel_jobCancel jobDELETECancels a running job by its UUID.get_jobGet jobGETRetrieves the status and details of a specific job by its UUID.import_project_mediaImport project mediaPOSTCreates an async import job to bring media files from URLs into a Descript project.list_jobsList jobsGETLists recent import and agent jobs with filtering and cursor-based pagination.
Project, 3 operations
get_projectGet projectGETRetrieves detailed metadata for a Descript project including media files and compositions.list_projectsList projectsGETLists Descript projects with optional filtering by name, creator, date range, and cursor-based pagination.publish_projectPublish projectPOSTSubmits an async job to publish a Descript project or composition as a shareable video or audio link.
Import, 1 operation
create_import_urlCreate import urlPOSTCreates a one-time import URL that redirects users to the Descript import UI for media file transfer.
Published project, 1 operation
get_published_projectGet published projectGETRetrieves metadata for a published Descript project including title, duration, publisher info, privacy, and subtitles.
Use Descript from Claude Code, Cursor or Codex
Connect Descript in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Descript operations become tools the client can call, next to every other integration you connected.
claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"
[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"{
"mcpServers": {
"livecontext": {
"type": "http",
"url": "https://livecontext.ai/mcp",
"headers": {
"X-API-Key": "YOUR_API_KEY"
}
}
}
}How to connect Descript
- Create your workspace
Sign up free. Nothing to install.
- Connect Descript once
Add your Descript connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
- Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.
Descript integration FAQ
What can you do with the Descript integration?
LiveContext exposes 10 operations on Descript, covering job, project, import and published project. Common uses include Browse all projects in a Descript drive, Inspect project contents before publishing and Retrieve metadata for a shared Descript project.
