Skip to main content
Glama
Red5d

Jupiter Broadcasting Podcast Data MCP Server

by Red5d

get_transcript

Retrieve podcast episode transcripts by providing show name and episode number. Access text content from Jupiter Broadcasting podcasts for analysis or reference.

Instructions

Get the transcript for a specific episode.

Args: show_name: Name of the show episode_number: Episode number

Returns: Dictionary containing the transcript text or error message.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
show_nameYes
episode_numberYes

Implementation Reference

  • Primary MCP tool handler registered with @mcp.tool(). Delegates to rss_parser.get_transcript, handles errors, and formats the response as a dictionary.
    @mcp.tool() def get_transcript(show_name: str, episode_number: str) -> Dict[str, Any]: """Get the transcript for a specific episode. Args: show_name: Name of the show episode_number: Episode number Returns: Dictionary containing the transcript text or error message. """ try: transcript = rss_parser.get_transcript(show_name, episode_number) if transcript: return {"transcript": transcript} else: return {"error": f"Transcript not available for episode '{episode_number}' in show '{show_name}'"} except Exception as e: return {"error": f"Failed to retrieve transcript: {str(e)}"}
  • Core implementation logic: retrieves the episode data, extracts the transcript URL, fetches and returns the transcript text.
    def get_transcript(self, show_name: str, episode_number: str) -> Optional[str]: """Get transcript for an episode.""" episode = self.get_episode(show_name, episode_number) if not episode: return None transcript_url = episode.get("transcript_url") if not transcript_url: return None try: response = requests.get(transcript_url, timeout=30) response.raise_for_status() return response.text except Exception as e: print(f"Error fetching transcript: {e}") return None
  • Extracts podcast:transcript XML elements during episode parsing to populate transcript_url used by get_transcript.
    transcript_elems = item.findall('.//{https://podcastindex.org/namespace/1.0}transcript') for transcript in transcript_elems: transcript_url = transcript.get("url") transcript_type = transcript.get("type", "") if transcript_url: episode_data["transcript_urls"].append({ "url": transcript_url, "type": transcript_type, "language": transcript.get("language", "en-us") }) # For backward compatibility, set transcript_url to the first available transcript if episode_data["transcript_urls"]: episode_data["transcript_url"] = episode_data["transcript_urls"][0]["url"] else: episode_data["transcript_url"] = None
  • Explicit registration of the get_transcript tool using FastMCP decorator.
    @mcp.tool()
  • Supporting function to locate the specific episode by GUID or podcast:episode number, required by get_transcript.
    def get_episode(self, show_name: str, episode_number: str) -> Optional[Dict[str, Any]]: """Get specific episode data.""" feed_root = self._get_feed(show_name) if feed_root is None: return None # Find all item elements (episodes) items = feed_root.xpath('//item') for item in items: # Check GUID guid_elem = item.find('guid') if guid_elem is not None and guid_elem.text == episode_number: return self._parse_episode(show_name, item) # Check podcast:episode number episode_elem = item.find('.//{https://podcastindex.org/namespace/1.0}episode') if episode_elem is not None and episode_elem.text == episode_number: return self._parse_episode(show_name, item)

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Red5d/jupiterbroadcasting_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server