Integrations

MCP server

Point any MCP-compatible AI client at TranscriptFetch so your assistant can fetch video transcripts, scrape web pages, and discover videos mid-conversation.

The server advertises six tools:

get_transcript, full transcript for a single video: YouTube ID/URL, plus TikTok, Instagram, X, Facebook, and direct media file URLs.
search_videos, search YouTube by keyword; returns titles, IDs, and URLs.
list_channel_videos , recent videos for a channel handle (@name), ID (UC…), or URL.
list_playlist_videos , videos in a playlist ID or URL.
scrape_url, any web page as clean Markdown (boilerplate removed), plus page metadata.
map_url, every same-site link on a page (sitemap included), for discovering what to scrape.

Claude (web), one-click connector

The fastest way to connect. Claude.ai handles authentication over OAuth, so no API key is needed for this path, you just sign in to TranscriptFetch and approve access. Requires a paid Claude plan (Pro, Max, Team, or Enterprise), which is where custom connectors are available.
  1. In Claude.ai, open Settings → Connectors and click “Add custom connector”.
  2. Set the name to TranscriptFetch and the server URL to https://transcriptfetch.com/mcp.
  3. Click “Connect”. You’re taken to TranscriptFetch’s sign-in / authorization page, sign in (or create an account) and approve access.
  4. Acknowledge that Claude will use your TranscriptFetch credits when it fetches (1 credit per successful fetch).
  5. Done. All six tools (get_transcript, search_videos, list_channel_videos, list_playlist_videos, scrape_url, map_url) are now available, paste a video URL from YouTube, TikTok, Instagram, X, or Facebook, or ask Claude to read any web page.

Claude Code / Desktop, API key

For Claude Code, add the server with your API key as a bearer header:

bash
claude mcp add --transport http transcriptfetch https://transcriptfetch.com/mcp \
  --header "Authorization: Bearer tf_live_YOUR_KEY"

For Claude Desktop, bridge the HTTP server with mcp-remote in your claude_desktop_config.json:

JSON
{
  "mcpServers": {
    "transcriptfetch": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://transcriptfetch.com/mcp",
        "--header",
        "Authorization: Bearer tf_live_YOUR_KEY"
      ]
    }
  }
}

Cursor / VS Code, API key

Add an entry to your MCP config (Cursor: ~/.cursor/mcp.json, VS Code: .vscode/mcp.json):

JSON
{
  "mcpServers": {
    "transcriptfetch": {
      "url": "https://transcriptfetch.com/mcp",
      "headers": {
        "Authorization": "Bearer tf_live_YOUR_KEY"
      }
    }
  }
}
Smitheryalso in the official MCP Registry.
Next →Versioning & changelog
MCP server · TranscriptFetch docs