Unprofane

Should I allow this text? Profanity and toxicity checks that are hard to fool, with the evidence.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
80%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~425token 数(工具定义)
~1014 B典型响应大小
对注意力的影响极小(占 128k 上下文窗口的 0.33%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "unprofane": {
      "url": "https://api.unprofane.com/mcp"
    }
  }
}

远程端点

https://api.unprofane.com/mcpstreamable-http

它能做什么

工具清单

工具(3)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢check_text(text, context, policy, mode, mask)

Decide whether a text should be allowed: profanity, slurs, threats and sexual language, including disguised spellings. Returns the action (allow, review, block), the evidence, a one-sentence reason and a censored version. Use context "username" for names shown publicly.

输入模式

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "maxLength": 10000
    },
    "context": {
      "type": "string",
      "enum": [
        "general",
        "username",
        "display_name",
        "comment",
        "chat",
        "gaming",
        "educational",
        "creative",
        "review",
        "custom_text"
      ]
    },
    "policy": {
      "type": "string",
      "enum": [
        "kids",
        "teen",
        "standard",
        "strict"
      ]
    },
    "mode": {
      "type": "string",
      "enum": [
        "fast",
        "balanced",
        "thorough"
      ]
    },
    "mask": {
      "type": "string",
      "enum": [
        "asterisk",
        "first_letter",
        "grawlix",
        "remove"
      ]
    }
  },
  "required": [
    "text"
  ]
}
🟢check_batch(items, context, policy)

Check up to 100 texts at once. Each item has an id and a text; results come back in order.

输入模式

{
  "type": "object",
  "properties": {
    "items": {
      "type": "array",
      "maxItems": 100,
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "text": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "text"
        ]
      }
    },
    "context": {
      "type": "string"
    },
    "policy": {
      "type": "string"
    }
  },
  "required": [
    "items"
  ]
}
🟢get_integration_snippet(platform, language)

A complete, runnable recipe for adding Unprofane to a platform (supabase, clerk, firebase, auth0, better-auth, unity, godot, or plain http) in a language.

输入模式

{
  "type": "object",
  "properties": {
    "platform": {
      "type": "string",
      "enum": [
        "http",
        "supabase",
        "clerk",
        "firebase",
        "auth0",
        "better-auth",
        "unity",
        "godot"
      ]
    },
    "language": {
      "type": "string",
      "enum": [
        "curl",
        "javascript",
        "typescript",
        "python",
        "csharp",
        "gdscript",
        "go",
        "php",
        "ruby"
      ]
    }
  },
  "required": [
    "platform",
    "language"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本3 个工具