MCP.so
Sign In
S

Sensitive Lexicon Mcp

@zephyrpersonal

Repository

About Sensitive Lexicon Mcp

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.

#sensitive-lexicon#word-detection#filtering

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Sensitive Lexicon Mcp?

Sensitive Lexicon Mcp is an MCP (Model Context Protocol) server built on the Sensitive-lexicon sensitive word library. It provides large language models (LLMs) with sensitive word detection and filtering capabilities, supporting multiple categories such as political, pornography, violence, and advertisement. It is designed for developers and users who need to moderate or redact sensitive content in AI applications.

How to use Sensitive Lexicon Mcp?

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.

Key features of Sensitive Lexicon Mcp

  • 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.

Use cases of Sensitive Lexicon Mcp

  • Automatically check user‑generated content for sensitive terms before displaying it.
  • Redact sensitive words in LLM outputs before exposing them to users.
  • Integrate into CI/CD pipelines to scan code comments or documentation for sensitive language.
  • Batch‑process a large corpus of text files to flag or sanitize sensitive content.
  • Build a content moderation layer inside a custom chat application or agent.

FAQ from Sensitive Lexicon Mcp

How do I install Sensitive Lexicon Mcp?

You can install it globally via npm install -g sensitive-lexicon-mcp or locally by cloning the Git repository and running npm install && npm run build.

What tools does Sensitive Lexicon Mcp provide?

It provides four tools: detect_sensitive_words, filter_sensitive_words, get_categories, and get_word_count. Each accepts JSON parameters and returns structured results.

Which sensitive word categories are supported?

The server includes 15 categories: covid19, gfw, other, subversive, advertisement, political, violence, livelihood, weapons, pornography-type, pornography, supplementary, corruption, tencent, and illegal-urls.

Can I customize the replacement text when filtering?

Yes. The filter_sensitive_words tool accepts an optional replacement parameter (default "***"). You can provide any string, like "[已屏蔽]".

Does the server require any external authentication or API key?

No. Sensitive Lexicon Mcp runs locally using the standard MCP stdio transport; it does not require any authentication or external API key. The lexicon is fetched from a public GitHub repository.

Frequently asked questions

How do I install Sensitive Lexicon Mcp?

You can install it globally via `npm install -g sensitive-lexicon-mcp` or locally by cloning the Git repository and running `npm install && npm run build`.

What tools does Sensitive Lexicon Mcp provide?

It provides four tools: `detect_sensitive_words`, `filter_sensitive_words`, `get_categories`, and `get_word_count`. Each accepts JSON parameters and returns structured results.

Which sensitive word categories are supported?

The server includes 15 categories: `covid19`, `gfw`, `other`, `subversive`, `advertisement`, `political`, `violence`, `livelihood`, `weapons`, `pornography-type`, `pornography`, `supplementary`, `corruption`, `tencent`, and `illegal-urls`.

Can I customize the replacement text when filtering?

Yes. The `filter_sensitive_words` tool accepts an optional `replacement` parameter (default `"***"`). You can provide any string, like `"[已屏蔽]"`.

Does the server require any external authentication or API key?

No. Sensitive Lexicon Mcp runs locally using the standard MCP stdio transport; it does not require any authentication or external API key. The lexicon is fetched from a public GitHub repository.

Comments

Basic information

Category

Other

Transports

stdio

Author

zephyrpersonal

Submitted by

Zhang Xin

More Other MCP servers

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

MCP Registry

modelcontextprotocol

A community driven registry service for Model Context Protocol (MCP) servers.

7.0K

Figs, Relationship Expert

Figs O'Sullivan, LMFT

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

XcodeBuildMCP

cameroncooke

A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

6.0K