Descript Complete
Provides full Descript integration for transcription, AI-powered editing, voice synthesis, and export. Automates audio/video processing including filler word removal, silence trimming, and project collaboration through natural language commands.
README
Descript Complete MCP Server
Stop manually transcribing audio. Upload recordings, get transcripts, remove filler words, and export edited content — all from your AI assistant.
What It Does
This MCP server gives your AI assistant full control over Descript: transcription, editing, AI voice (Overdub), collaboration, and export — all via natural language.
Tools
| Tool | Category | Description |
|---|---|---|
transcribe_audio |
Transcription | Submit an audio URL for transcription |
transcribe_video |
Transcription | Submit a video URL for transcription |
get_transcript |
Transcription | Fetch transcript by share slug (text, JSON, or VTT) |
list_transcripts |
Transcription | List recent transcription jobs |
create_project |
Projects | Create a new Descript project |
list_projects |
Projects | List all projects in your account |
get_project |
Projects | Get details for a specific project |
delete_project |
Projects | Delete a project permanently |
upload_media |
Media | Upload media to a project via URL |
get_upload_status |
Media | Check upload/processing job status |
remove_filler_words |
Editing | Remove um, uh, like, etc. with AI |
remove_silence |
Editing | Remove silent gaps automatically |
trim_transcript |
Editing | Edit content via natural language instruction |
export_transcript_txt |
Export | Export transcript as plain text |
export_transcript_srt |
Export | Export transcript as SRT subtitles |
export_video |
Export | Render/export the video |
create_overdub |
Overdub | Generate speech with AI voice |
list_overdub_voices |
Overdub | List available AI voices |
get_project_members |
Collaboration | Get project collaborators |
share_project |
Collaboration | Invite a collaborator by email |
Quick Start
- Get your Descript API key from your Descript account settings
- Set
DESCRIPT_API_KEY=your_key_herein your environment - Start the server:
npm start - Connect your MCP client to
http://localhost:8080/mcp
Example Workflows
Transcribe a podcast episode:
transcribe_audio({ url: "https://example.com/episode-42.mp3", project_name: "Episode 42" })
// Returns job_id — poll with get_upload_status until state = "stopped"
// Then get_transcript({ slug: "your-share-slug", format: "text" })
Clean up an interview recording:
remove_filler_words({ project_id: "abc123" })
remove_silence({ project_id: "abc123", threshold_seconds: 0.8 })
export_transcript_txt({ slug: "your-share-slug", include_speakers: true })
Share for review:
share_project({ project_id: "abc123", email: "editor@example.com", role: "editor" })
Environment Variables
| Variable | Required | Description |
|---|---|---|
DESCRIPT_API_KEY |
Yes | Your Descript API key |
PORT |
No | Server port (default: 8080) |
Health Check
GET http://localhost:8080/health
# {"status":"ok","server":"descript-complete","version":"1.0.0"}
Built with the MCPize framework. Powered by mastermindshq.business.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.