MCP Podcast Scraper

You can run the MCP Podcast Scraper as a local MCP server to automatically fetch, transcribe, and summarize podcast episodes from YouTube or RSS feeds. It organizes outputs by podcast and episode, tracks new content, avoids duplicates, and lets you tailor summaries with custom prompts for Claude integrations.

How to use

To use this MCP server, run it locally and connect your Claude MCP client. The server can check tracked podcasts for new episodes, scrape and transcribe them, and generate summaries using your custom prompt. You can then save transcripts and summaries in an organized folder structure and reuse the workflow across multiple podcasts.

How to install

Prerequisites and setup steps are outlined below. Follow them in order to have a working MCP server you can connect to from Claude Code or Claude Desktop.

# Install Homebrew if you don't have it (macOS)
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

# Install required tools
brew install yt-dlp ffmpeg

Clone the project, install dependencies, and build the server.

# Clone the repository
git clone https://github.com/wkoleilat-happytitan/mcp-podcast-scraper.git
cd mcp-podcast-scraper

# Install dependencies
npm install

# Build the project
npm run build

Obtain a Deepgram API key for transcription. Create a config file and insert your key.

# Copy the example config
cp config.example.json config.json

# Edit config.json and add your Deepgram API key
# Example content:
# {
#   "outputDirectory": "./podcasts",
#   "deepgramApiKey": "YOUR_ACTUAL_DEEPGRAM_API_KEY",
#   "tempDirectory": "./temp"
# }

Configure the MCP connection in Claude Code or Claude Desktop by providing the path to the compiled server entry point.

{
  "mcpServers": {
    "podcast_scraper": {
      "command": "node",
      "args": ["/FULL/PATH/TO/mcp-podcast-scraper/dist/index.js"]
    }
  }
}

Available tools

scrape_podcast

Scrape and transcribe a podcast episode from YouTube or RSS feeds, preparing the transcript for summarization.

get_transcript

Read the full transcript of a scraped episode for reference or reuse.

get_summary_prompt

Retrieve your customized instructions that guide how Claude summarizes each episode.

save_summary

Save the generated summary to a markdown file alongside the transcript.

check_new_episodes

Check tracked podcasts for new (unscraped) episodes to process.

list_incomplete

Identify episodes that have transcripts but are missing summaries.

search_podcast

Find episodes by searching YouTube or parsing RSS feeds for new content.

add_tracking

Add a podcast RSS feed to your tracking list for automatic monitoring.

list_tracking

List all podcasts you are currently tracking.

remove_tracking

Remove a podcast from your tracking list.