中国 AI 合规与备案(条文级自查) MCP server
cn.savantcat/ai-compliancesavantcat.cnstreamable-httpv1.1.1Scanned
生成式AI备案、AI生成内容标识、深度合成、算法备案:条文级问答 + 按条号取法规原文 + 应办清单(中文)
8 tools: 3 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
Anlyon alternative
3 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the 中国 AI 合规与备案(条文级自查) MCP server can do
The 中国 AI 合规与备案(条文级自查) MCP server is published by savantcat.cn, a domain the MCP Registry verified. It has 8 tools. It can create or change data (3 tools: self_check, filing_route and regulation_info), but cannot delete data. 5 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Oct 29, 2026, version 1.1.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Changes things 3Claude Code: ask
filing_route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。 Args: public_facing: 是否面向中国境内公众提供服务(仅内部使用请传 false) generates_content: 是否能生成文本/图片/音频/视频等内容 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、…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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。 Args: public_facing: 是否面向中国境内公众提供服务(仅内部使用请传 false) generates_content: 是否能生成文本/图片/音频/视频等内容 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) only_internal_use: 是否仅企业内部使用、不对外提供
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
regulation_info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)。No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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)。
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
self_check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。 Args: scope: 场景或关键词,如「AI 客服」「营销文案 标注」「小程序 上架」「全量」; 留空则返回全量自查清单No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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。 Args: scope: 场景或关键词,如「AI 客服」「营销文案 标注」「小程序 上架」「全量」; 留空则返回全量自查清单
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
Only reads 5Show 5 read-only tools
get_article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。 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); get_article 按「条号」取条文原文,用于逐字核对、引用与溯源。 Args: 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》)、 简…No findings
Why it is in this group
- The name "get_article" says "get": a word for reading.
Description, as the server wrote it 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。 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); get_article 按「条号」取条文原文,用于逐字核对、引用与溯源。 Args: 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》)、 简称(标识办法 / 算法推荐规定)或 cluster (genai-interim / ai-content-label / deep-synthesis / algo-recommendation) article: 条号,支持「第十条」「10」「第10条」三种写法
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_requirement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)。 Args: slug: 条目标识,先用 list_topics 或 search_compliance 取得No findings
Why it is in this group
- The name "get_requirement" says "get": a word for reading.
Description, as the server wrote it 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)。 Args: slug: 条目标识,先用 list_topics 或 search_compliance 取得
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
list_topics列出全部合规条目的标题清单。 Args: cluster: 可选,按集群过滤。可选值 genai-interim(生成式AI暂行办法) / ai-content-label(AI生成合成内容标识) / deep-synthesis(深度合成) / algo-recommendation(算法推荐与备案) / filing-practice(备案实操)No findings
Why it is in this group
- The name "list_topics" says "list": a word for reading.
Description, as the server wrote it 列出全部合规条目的标题清单。 Args: cluster: 可选,按集群过滤。可选值 genai-interim(生成式AI暂行办法) / ai-content-label(AI生成合成内容标识) / deep-synthesis(深度合成) / algo-recommendation(算法推荐与备案) / filing-practice(备案实操)
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
search_articles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。 用途:已经知道是哪部法规,要定位「哪一条讲了这件事」。 Args: law: 法规名或集群标识(同 get_article 的 law 参数) keywords: 检索词,如「训练数据 合法来源」「标识 元数据」「备案 十日」 top_k: 返回条数,默认 5No findings
Why it is in this group
- The name "search_articles" says "search": a word for reading.
Description, as the server wrote it 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。 用途:已经知道是哪部法规,要定位「哪一条讲了这件事」。 Args: law: 法规名或集群标识(同 get_article 的 law 参数) keywords: 检索词,如「训练数据 合法来源」「标识 元数据」「备案 十日」 top_k: 返回条数,默认 5
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
search_compliance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)。 Args: 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」 top_k: 返回条数,默认 5No findings
Why it is in this group
- The name "search_compliance" says "search": a word for reading.
Description, as the server wrote it 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)。 Args: 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」 top_k: 返回条数,默认 5
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:32 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://savantcat.cn/mcp-compliance: tools/list returned 8 tools to an anonymous client, including self_check (write), filing_route (write), regulation_info (write)
Posture changes
- Nov 6, 2026
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 3
- Protocol version: none to 2025-06-18
- Oct 29, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: no -> yes; HTTP status of an anonymous initialize: none -> 200; tools/list served without credentials: no -> yes (and 2 more).View diff
- Reachable: no to yes
- HTTP status of an anonymous initialize: none to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 3
- Protocol version: none to 2025-06-18
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 2 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.1.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http ai-compliance https://savantcat.cn/mcp-complianceclaude mcp add --transport http ai-compliance https://savantcat.cn/mcp-complianceRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__ai-compliance__list_topics",
"mcp__ai-compliance__search_compliance",
"mcp__ai-compliance__get_requirement",
"mcp__ai-compliance__get_article",
"mcp__ai-compliance__search_articles"
],
"ask": [
"mcp__ai-compliance__self_check",
"mcp__ai-compliance__filing_route",
"mcp__ai-compliance__regulation_info"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as ai-compliance. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/cn.savantcat/ai-compliance/verify?hash=1307e73f04522af5045aadfb3c58d0050bc77796738563c45677ab8d64de6455" | jq -e '.changed == false'Pinned hash 1307e73f0452, from Oct 29, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/cn.savantcat/ai-compliance/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/cn.savantcat/ai-compliance)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:46 UTC.
中国 AI 合规与备案(条文级自查) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the 中国 AI 合规与备案(条文级自查) MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 3 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the 中国 AI 合规与备案(条文级自查) MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the 中国 AI 合规与备案(条文级自查) MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the 中国 AI 合规与备案(条文级自查) MCP server have?
- 8 tools: 3 write, 5 read. self_check, filing_route, regulation_info, list_topics, search_compliance, get_requirement, get_article and search_articles.
Does the 中国 AI 合规与备案(条文级自查) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the 中国 AI 合规与备案(条文级自查) MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the 中国 AI 合规与备案(条文级自查) MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 29, 2026.