get_transcript

Instructions

Implementation Reference

• main.py:260-302 (handler)

  The main handler function for the 'get_transcript' MCP tool. It extracts the video ID, fetches the transcript via YouTubeTranscriptApi, optionally adds timestamps, formats the output (text/json/pretty/webvtt/srt), and optionally prepends a metadata block.

  @mcp.tool()
  def get_transcript(
      url: str,
      languages: list[str] | None = None,
      format: str = "text",
      preserve_formatting: bool = False,
      include_timestamps: bool = False,
      include_metadata: bool = True,
  ) -> str:
      """Fetch a YouTube video's transcript.
  
      Args:
          url: YouTube video URL or video ID
          languages: Preferred languages in priority order (e.g. ["en", "de"]). Defaults to English.
          format: Output format — one of: text, json, pretty, webvtt, srt
          preserve_formatting: Keep HTML formatting tags in the transcript text
          include_timestamps: When True with format="text", prefix each line with [HH:MM:SS]. Ignored for json/srt/webvtt/pretty (those formats already include timestamps).
          include_metadata: When True (default), prepend a [METADATA] block (title, channel, published, duration, views, description) before the transcript. Pass False for transcript-only output.
      """
      try:
          video_id = extract_video_id(url)
      except ValueError as e:
          return f"Error: {e}"
  
      langs = languages or ["en"]
      try:
          transcript = api.fetch(
              video_id,
              languages=langs,
              preserve_formatting=preserve_formatting,
          )
          if include_timestamps and format == "text":
              body = _format_transcript_with_timestamps(transcript)
          else:
              body = _format_transcript(transcript, format)
      except Exception as e:
          return _handle_transcript_error(e, video_id, langs)
  
      if not include_metadata:
          return body
  
      meta = _fetch_metadata(video_id)
      return f"{_format_metadata_block(meta)}\n\n[TRANSCRIPT]\n{body}"

• main.py:260-260 (registration)

  The @mcp.tool() decorator registers 'get_transcript' as an MCP tool on the FastMCP server instance.

  @mcp.tool()

• main.py:40-48 (helper)

  Helper function extract_video_id() used to parse a YouTube URL or bare video ID from the user-provided URL argument.

  def extract_video_id(url_or_id: str) -> str:
      """Extract a YouTube video ID from a URL or bare ID string."""
      url_or_id = url_or_id.strip()
      if BARE_ID_REGEX.match(url_or_id):
          return url_or_id
      match = VIDEO_ID_REGEX.search(url_or_id)
      if match:
          return match.group(1)
      raise ValueError(

• main.py:66-71 (helper)

  Helper _format_transcript() used to format the transcript using the selected formatter (text, json, pretty, webvtt, srt).

  def _format_transcript(transcript, fmt: str) -> str:
      """Format a FetchedTranscript using the specified formatter."""
      formatter = FORMATTERS.get(fmt)
      if formatter is None:
          return f"Error: Unknown format '{fmt}'. Choose from: {', '.join(FORMATTERS)}"
      return formatter.format_transcript(transcript)

• main.py:115-119 (helper)

  Helper _format_transcript_with_timestamps() used to render transcript as text with [HH:MM:SS] prefixes when include_timestamps=True.

  def _format_transcript_with_timestamps(transcript) -> str:
      """Render a FetchedTranscript as text with an [HH:MM:SS] prefix on each line."""
      return "\n".join(
          f"{_format_timestamp(snippet.start)} {snippet.text}" for snippet in transcript
      )