PodCrawlerMCP
About
PodCrawlerMCP is an MCP (Model Context Protocol) server that enables AI assistants to discover podcast episodes on specific topics by crawling the web for RSS feeds. It crawls podcast directories, parses feeds, filters episodes by topic or domain, and exposes this functionality as MCP tools.
Details
- License
- MIT license
Explore
- 🕸️ 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
PodCrawlerMCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
pip install podcrawler-mcp
Or with Poetry:
poetry add podcrawler-mcp
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"podcrawlermcp": {
"podcrawler-mcp": {
"command": "python",
"args": [
"-m",
"podcrawler.server"
]
}
}
}
}
McpServers
{
"podcrawler-mcp": {
"command": "python",
"args": [
"-m",
"podcrawler.server"
]
}
}
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.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



