Wanhe AI Compliance Checker

top.wanhetoolsPublished by wanhetools.topOfficial publisherv1.0.1Updated Oct 27, 2026

AI content compliance: ad-law prohibited words, AI labeling GB45438, EU AI Act Art50, SB1000

VerifiedStreamable HTTPWeb executableSecurity & MonitoringBusiness & Commerce

Overview

AI-generated overview

Remote MCP server that checks Chinese marketing copy against Chinese advertising-law rules and flags AI-generated content labeling issues.

What you can do
  • Check a piece of Chinese content for advertising-law compliance risk, returning a per-item list of issue type, source position, matched text, cited legal article and suggested fix.
  • Detect wording that suggests AI-generated or synthesized content and get reminders about China's AI content labeling rules.
  • Coverage includes absolute-superlative wording, medical efficacy and disease claims, health-food claims, banned phrases and false statements.
When to use it
Useful when drafting or reviewing Chinese ad copy, product pages or marketing text and you want a quick rule-based risk scan before publishing, or when you need a reminder about AI content labeling obligations.
Requirements
A remote streamable HTTP endpoint; no package, environment variable or header is declared. No authentication is declared. Each call is limited to 2000 characters and the session allows 30 calls in total.
Before you install
The check is a rule-based screening aid, not legal advice, and the free tier only detects AI-related wording rather than full explicit and metadata labeling verification. Content you submit is sent to a third-party remote service. Usage is capped per session.

Installation

In SourceWeft

  1. Open Wanhe AI Compliance Checker in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/top.wanhetools%2Fcompliance/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "wanhe-ai-compliance-checker": {
      "type": "http",
      "url": "https://wanhetools.top/mcp"
    }
  }
}

Tools

2

check_content

检查一段中文内容的广告法合规风险，返回逐条问题清单：问题类型 / 原文位置 / 命中文本 / 依据法条 / 修改建议。覆盖：绝对化用语（第9条）、医疗功效与疾病名（第17/18条）、保健功效、违规用语（免检/特供）、食品绝对化、虚假表述等高频规则。调用规则：同输入必同输出；未发现问题时明确说明，不虚报。限制：单次 2000 字符；本会话共 30 次。

Parameterslangtextrequired

check_ai_label

检测内容中的 AI 生成/合成表述，并提示《人工智能生成合成内容标识办法》的标识要求。免费版只做表述检测；完整判定（显式标识 + 隐式元数据标识）在云端版。

Parameterstextrequired

Version history

2
  1. v1.0.1LatestOct 21, 2026
  2. v1.0.0Oct 18, 2026

Score

72% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts

    Publish an icon in the registry entry.

  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.