What is Podcrawler Mcp

Podcrawler-mcp is an MCP (Model Context Protocol) server designed for podcast discovery through web crawling. It enables AI assistants to find podcast episodes on specific topics by crawling the web for RSS feeds.

Use cases

Use cases include discovering podcasts on specific topics like technology or history, integrating with AI assistants for enhanced user experience, and providing curated podcast recommendations based on user interests.

How to use

To use podcrawler-mcp, install it via pip or Poetry. Run the server directly using ‘python -m podcrawler.server’ or integrate it into your Python code by creating an instance of PodCrawlerServer and calling the run method.

Key features

Key features include crawling podcast directories to discover RSS feeds, parsing RSS feeds to extract episode data, filtering episodes by topic or domain, exposing functionality through MCP tools, and seamless integration with AI assistants like Claude.

Where to use

Podcrawler-mcp can be used in various fields such as media, education, and technology, where podcast content is relevant for discovery and analysis.

PodCrawlerMCP

An MCP (Model Context Protocol) server for podcast discovery through web crawling. PodCrawlerMCP enables AI assistants to find podcast episodes on specific topics by crawling the web for RSS feeds.

Features

• 🕸️ Crawls podcast directories to discover RSS feeds
• 🎙️ Parses RSS feeds to extract episode data
• 🔍 Filters episodes by topic or domain
• 🔌 Exposes functionality through MCP tools
• 🤖 Seamlessly integrates with AI assistants like Claude

Installation

pip install podcrawler-mcp

Or with Poetry:

poetry add podcrawler-mcp

Quick Start

Run the server directly:

python -m podcrawler.server

Or in your Python code:

from podcrawler import PodCrawlerServer

server = PodCrawlerServer()
server.run()

Integrating with Claude Desktop

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "podcrawler": {
      "command": "python",
      "args": [
        "-m",
        "podcrawler.server"
      ]
    }
  }
}

Available Tools

discover_podcasts

Discovers podcasts on a specific topic.

Parameters:

• topic (string): The topic to search for (e.g., “technology”, “history”)
• max_results (integer, optional): Maximum number of results to return (default: 10)

Example Usage:

What are some science podcasts about black holes?

Project Structure

podcrawler-mcp/
├── podcrawler/                # Main package
│   ├── __init__.py            # Package initialization
│   ├── server.py              # MCP server implementation
│   ├── tools/                 # MCP tools
│   │   ├── __init__.py
│   │   └── discovery.py       # Podcast discovery tool
│   ├── crawler/               # Web crawling components
│   │   ├── __init__.py
│   │   ├── spider.py          # Web crawler implementation
│   │   └── parser.py          # RSS feed parser
│   └── utils/                 # Utility functions
│       ├── __init__.py
│       ├── filtering.py       # Topic filtering utilities
│       └── formatting.py      # Output formatting utilities
├── tests/                     # Tests
│   ├── __init__.py
│   └── test_server.py         # Server tests
├── examples/                  # Usage examples
│   └── basic_discovery.py     # Basic discovery example
├── pyproject.toml             # Project configuration
├── README.md                  # Project documentation
├── LICENSE                    # MIT License
└── CONTRIBUTING.md            # Contribution guidelines

Development

1. Clone the repository

   git clone https://github.com/infinitimeless/podcrawler-mcp.git
   cd podcrawler-mcp
   

2. Install dependencies using Poetry

   poetry install
   

3. Run tests

   poetry run pytest
   

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for details.

License

This project is licensed under the MIT License - see the LICENSE file for details.