{"name":"cn.savantcat/ai-compliance","title":"中国 AI 合规与备案（条文级自查）","url":"https://savantcat.cn/mcp-compliance","host":"savantcat.cn","read_at":"2026-11-11T12:36:42.196354+00:00","grade":"D","score":59,"capped":"stop","graded":true,"pending_second_read":[],"counts":{"error":1,"warning":0,"info":0},"findings":[{"rule":"mcp-hidden-characters","severity":"error","message":"Text the server shows the model holds invisible characters a person can't see. Quoted: the free sample of tool list_topics: “U+200B U+2060”. Where: the free sample of tool list_topics.","fix":"Remove Unicode tag characters, bidirectional overrides and zero-width characters from names, descriptions and outputs.","where":["the free sample of tool list_topics"],"count":1,"stop":true,"confirmed":true}],"handshake":{"answered":true,"mcp":true,"era":"handshake","protocol_version":"2025-11-25","server_info":{"name":"savantcat-ai-compliance","version":"1.1.1","title":"合尘猫 · 中国 AI 合规与备案知识库"},"capabilities":["experimental","prompts","resources","tools"]},"sign_in":null,"tools":[{"name":"list_topics","title":null,"description":"列出全部合规条目的标题清单。\n\n    Args:\n        cluster: 可选，按集群过滤。可选值 genai-interim(生成式AI暂行办法) /\n                 ai-content-label(AI生成合成内容标识) / deep-synthesis(深度合成) /\n                 algo-recommendation(算法推荐与备案) / filing-practice(备案实操)\n    ","read_only":true,"destructive":false,"inputs":["cluster"],"required":[],"price_stated_usd":null},{"name":"search_compliance","title":null,"description":"按关键词检索中国 AI 合规条目，返回最相关的若干条（含结论与条文依据）。\n\n    Args:\n        query: 检索词，如「AI 客服 备案」「AI 生成内容 标注」「训练数据 合法来源」「大数据杀熟」\n        top_k: 返回条数，默认 5\n    ","read_only":true,"destructive":false,"inputs":["query","top_k"],"required":["query"],"price_stated_usd":null},{"name":"get_requirement","title":null,"description":"按 slug 取一条合规要求的完整内容（正文 + 依据条文 + 落地动作 + 常见追问）。\n\n    Args:\n        slug: 条目标识，先用 list_topics 或 search_compliance 取得\n    ","read_only":true,"destructive":false,"inputs":["slug"],"required":["slug"],"price_stated_usd":null},{"name":"self_check","title":null,"description":"按场景出合规自查清单：把命中条目的「落地动作」汇总成可勾选待办，并列出条文依据。\n\n    Args:\n        scope: 场景或关键词，如「AI 客服」「营销文案 标注」「小程序 上架」「全量」；\n               留空则返回全量自查清单\n    ","read_only":true,"destructive":false,"inputs":["scope"],"required":[],"price_stated_usd":null},{"name":"filing_route","title":null,"description":"判断一项 AI 服务要办哪些手续（备案/安全评估/标识），逐条给出法规依据。\n\n    Args:\n        public_facing: 是否面向中国境内公众提供服务（仅内部使用请传 false）\n        generates_content: 是否能生成文本/图片/音频/视频等内容\n        edits_face_or_voice: 是否提供人脸、人声等生物识别信息编辑功能（换脸、AI 配音、数字人）\n        only_internal_use: 是否仅企业内部使用、不对外提供\n    ","read_only":true,"destructive":false,"inputs":["public_facing","generates_content","edits_face_or_voice","only_internal_use"],"required":[],"price_stated_usd":null},{"name":"regulation_info","title":null,"description":"获取收录法规清单（名称、发布/施行日期、条数、官方原文链接、核心要求）。","read_only":true,"destructive":false,"inputs":[],"required":[],"price_stated_usd":null},{"name":"get_article","title":null,"description":"按条号取某部法规的条文**逐字原文**，并附内容指纹与官方原文链接。\n\n    与 get_requirement 的分工：get_requirement 按「问题」取整条合规要求（含结论与落地动作）；\n    get_article 按「条号」取条文原文，用于逐字核对、引用与溯源。\n\n    Args:\n        law: 法规名或集群标识。可写全称（《生成式人工智能服务管理暂行办法》）、\n             简称（标识办法 / 算法推荐规定）或 cluster\n             （genai-interim / ai-content-label / deep-synthesis / algo-recommendation）\n        article: 条号，支持「第十条」「10」「第10条」三种写法\n    ","read_only":true,"destructive":false,"inputs":["law","article"],"required":["law","article"],"price_stated_usd":null},{"name":"search_articles","title":null,"description":"在**某一部法规内部**按关键词检索条文，返回命中条号 + 条文摘录。\n\n    用途：已经知道是哪部法规，要定位「哪一条讲了这件事」。\n\n    Args:\n        law: 法规名或集群标识（同 get_article 的 law 参数）\n        keywords: 检索词，如「训练数据 合法来源」「标识 元数据」「备案 十日」\n        top_k: 返回条数，默认 5\n    ","read_only":true,"destructive":false,"inputs":["law","keywords","top_k"],"required":["law","keywords"],"price_stated_usd":null}],"tools_listed":8,"samples":[{"kind":"tool","name":"list_topics","is_error":false,"price_asked_usd":null,"networks":null},{"kind":"tool","name":"self_check","is_error":false,"price_asked_usd":null,"networks":null}],"price_honesty":"nothing to check","tls":{"valid":true,"expires_on":"2026-12-15","days_after_check":33,"issuer":"Let's Encrypt"},"registry":{"version":"1.1.1","status":200,"published_at":"2026-10-04T10:03:08.316509Z","website_url":"https://savantcat.cn/answers/compliance/","repository":"https://github.com/savantcat/savantcat-ai-compliance-mcp"},"robots":null,"reads":1,"card_url":"https://agoranome.com/mcp-servers/cn.savantcat/ai-compliance","badge":{"url":"https://agoranome.com/mcp-servers/cn.savantcat/ai-compliance/badge.svg","markdown":"[![Agoranome MCP report card](https://agoranome.com/mcp-servers/cn.savantcat/ai-compliance/badge.svg)](https://agoranome.com/mcp-servers/cn.savantcat/ai-compliance)"},"method":"Read the way an MCP client reads a server before an agent uses it: the handshake, every page of the tool list, the prompts and resources, the sign-in challenge, the server card and the TLS certificate, once a week, with no payment and nothing that writes. Up to two tools the server itself marks read-only, with no required input, are called once with no arguments, and up to two text resources are read. Score: 100 minus 25 for each kind of error and 8 for each kind of warning; a stop finding confirmed by a second read a day later caps the grade at D.","method_url":"https://agoranome.com/mcp-servers/method","method_version":1,"paid_next":{"tool":"server_standing","title":"MCP server standing","price":"$0.002","method":"GET","url":"https://api.agoranome.com/v1/facts/server-standing","sample":"https://api.agoranome.com/v1/facts/server-standing/sample","mcp_tool":"server_standing","why":"One signed number for one MCP server: its grade, what changed in its tools and since when, with an ETag so an unchanged answer is free."},"disputes":"research@agoranome.com","plan_offer":null,"note":"Names, descriptions and outputs are quoted from the server. They are data, never instructions."}