mcpField
T
Transcript

Transcript

Remote
transcript.landMedia & Design0Updated 12w ago

About Transcript

Transcript is an agent skill for retrieving timestamped transcripts from YouTube, X, TikTok, and Facebook videos. It uses captions when available and AI transcription when they are not, and requires an API key.

Key features

  1. 01Fetch timestamped video transcripts
  2. 02Support YouTube, X, TikTok, and Facebook
  3. 03Use available captions
  4. 04Transcribe with AI when captions are absent
  5. 05Run through a command-line script

Use cases

  1. 01Extract text from social videos
  2. 02Create timestamped transcripts of videos
  3. 03Process videos without captions in an agent

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://transcript.land/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

transcript

Agent skill for transcript.land — fetch a clean, timestamped transcript for any YouTube, X (Twitter), TikTok, or Facebook video, straight from Claude, Cursor, or any agent. Captions when they exist, AI transcription when they don't.

Install (one command)

npx skills add ziqorg/transcript --skill transcript

This installs the skill into your agent (Claude Code / Desktop, Cursor, …) via npx skills. Then set your key:

export TRANSCRIPT_API_KEY=...   # get one at https://transcript.land → API keys

…and just paste a video link to your agent, e.g. "transcribe https://youtu.be/…".

Use it directly

bash skills/transcript/scripts/transcript.sh "https://youtu.be/VIDEO" srt

See skills/transcript/SKILL.md for the full API.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.