peterkemeling/sinterklaasgedichten-mcp
If you are the rightful owner of sinterklaasgedichten-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
The Rijmwoorden MCP Server is designed to assist AI chatbots in generating Dutch poetry by providing rhyming words and synonyms.
Rijmwoorden MCP Server
An MCP (Model Context Protocol) server that provides Dutch rhyming words and synonyms to AI chatbots, specifically designed for writing Sinterklaas poems and other Dutch poetry.
What it does
This server exposes two resources that AI assistants can query:
- rijmwoorden://{woord} - Returns rhyming words by scraping rijmwoordenboek.nl
- synoniemen://{woord} - Returns synonyms by scraping synoniemenboek.nl
It also includes a prompt template that guides AI assistants to write grammatically correct Dutch poems with proper rhymes and vivid imagery.
How it works
The server uses the FastMCP framework to expose resources via the Model Context Protocol. When an AI assistant needs rhyming words or synonyms:
- It queries the appropriate resource (e.g.,
rijmwoorden://pijn) - The server scrapes the corresponding website using httpx + BeautifulSoup
- Results are parsed and returned to the AI assistant
- The assistant uses these results to construct well-formed Dutch poems
Installation & Usage
# Install dependencies (uses uv for dependency management)
uv sync
# Run the server
uv run main.py
The server runs on the streamable-http transport and can be integrated with any MCP-compatible AI chatbot (Claude Desktop, etc.).
Integration with chatbots
To use this with Claude Desktop, add to your config file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"rijmwoorden": {
"command": "uv",
"args": ["run", "/path/to/rijmwoorden-mcp/main.py"]
}
}
}
Technical details
- Built with FastMCP
- Web scraping with httpx and BeautifulSoup4
- Python 3.12+
- Error handling for network timeouts and HTTP errors
Note
This is a prototype that scrapes the public websites. For production use, a proper API integration would be preferable for performance and reliability.