A Model Context Protocol (MCP) server that provides sensitive word detection and filtering capabilities for Large Language Models (LLMs), powered by the comprehensive https://github.com/konsheng/Sensitive-lexicon Chinese word database.
Overview
what is Sensitive Lexicon MCP?
Sensitive Lexicon MCP is a Model Context Protocol (MCP) server that provides sensitive word detection and filtering capabilities for Large Language Models (LLMs), utilizing a comprehensive Chinese word database.
how to use Sensitive Lexicon MCP?
To use Sensitive Lexicon MCP, you can install it via NPM or clone the repository from GitHub. After installation, configure it in your application to detect and filter sensitive words in text.
key features of Sensitive Lexicon MCP?
- Sensitive word detection in text
- Filtering and replacing sensitive words
- Support for multiple categories such as political, pornography, violence, and advertisements
- Real-time updates from the GitHub repository
- Easy integration with various LLMs using standard MCP protocol
use cases of Sensitive Lexicon MCP?
- Detecting sensitive words in user-generated content
- Filtering sensitive language in chat applications
- Ensuring compliance with content regulations in publishing platforms
FAQ from Sensitive Lexicon MCP?
- Can Sensitive Lexicon MCP detect all types of sensitive words?
Yes! It supports various categories of sensitive words including political, violence, and more.
- Is Sensitive Lexicon MCP easy to integrate?
Yes! It is designed for easy integration with different applications using the MCP protocol.
- How can I update the sensitive word database?
The database updates automatically from the GitHub repository.
Server Config
{
"mcpServers": {
"sensitive-lexicon": {
"command": "npx",
"args": [
"sensitive-lexicon-mcp"
]
}
}
}