Sensitive Lexicon Mcp

by zephyrpersonal

330 downloads
Not rated
GitHub

About

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.

Details

Author
zephyrpersonal
Downloads
330
Categories
Other

- Detects sensitive words in any given text.
- Filters (replaces) sensitive words with a customizable string.
- Supports 15 categories of sensitive words (political, violence, pornography, etc.).
- Real‑time lexicon updates fetched from a GitHub repository.
- Standard MCP protocol for easy integration with any MCP‑compatible client.
- Provides helper tools: get_categories and get_word_count.

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:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Sensitive Lexicon Mcp
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install globally via npm install -g sensitive-lexicon-mcp or locally in a project. Configure it as an MCP server in supported clients (Claude Desktop, Continue.dev, Cline, Zed, Cursor) by adding a JSON entry with npx sensitive-lexicon-mcp. The server exposes tools like detect_sensitive_words and filter_sensitive_words that accept text and optional categories or replacement parameters. Environment variables (SENSITIVE_UPDATE_INTERVAL, SENSITIVE_CACHE_SIZE, DEBUG) allow customization.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "sensitive lexicon mcp": {
            "sensitive-lexicon": {
                "command": "npx",
                "args": [
                    "sensitive-lexicon-mcp"
                ]
            }
        }
    }
}

McpServers

{
    "sensitive-lexicon": {
        "command": "npx",
        "args": [
            "sensitive-lexicon-mcp"
        ]
    }
}

Sensitive Lexicon MCP Server

MCP Badge

一个基于 Sensitive-lexicon 敏感词库的 MCP (Model Context Protocol) 服务器,为LLM提供敏感词检测和过滤功能。

功能特性

- 敏感词检测: 检测文本中的敏感词汇
- 敏感词过滤: 替换文本中的敏感词汇
- 多分类支持: 支持政治、色情、暴力、广告等多种敏感词分类
- 实时更新: 从GitHub仓库实时获取最新的敏感词库
- 易于集成: 标准MCP协议,易于与各种LLM集成

快速开始

方式一:NPM安装(推荐)

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.