General Tools

savantcat.cn

Provides general-purpose tools through the Model Context Protocol.

3 endpoints10 known toolsFirst detected September 11, 2026Last detected September 11, 2026

ENDPOINT 1

https://savantcat.cn/mcp

No auth detected

Known tools 0

No tool metadata was available in the registry cache.

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.savantcat-cn]
url = "https://savantcat.cn/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "savantcat-cn": {
      "type": "http",
      "url": "https://savantcat.cn/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: savantcat-cn
Remote MCP URL: https://savantcat.cn/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "savantcat-cn": {
      "url": "https://savantcat.cn/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "savantcat-cn": {
      "type": "http",
      "url": "https://savantcat.cn/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "savantcat-cn",
  "transport": "streamable-http",
  "url": "https://savantcat.cn/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://savantcat.cn/mcp-compliance

No auth detected

MCP server metadata

Name: savantcat-ai-compliance

Capabilities

experimentalpromptsresourcestools

Server instructions

合尘猫 · 中国 AI 合规与备案知识库。收录《生成式人工智能服务管理暂行办法》《人工智能生成合成内容标识办法》《互联网信息服务深度合成管理规定》《互联网信息服务算法推荐管理规定》的逐条要求，回答「要不要备案」「要不要标注 AI 生成」「AI 客服上线前要做什么」「用第三方大模型 API 义务在谁身上」这类问题。所有结论均标注法规条文依据，并用 filing_route 给出应办事项清单。

Known tools 6

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)

Inferred read-only

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 5

Inferred read-only

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

Inferred read-only

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

Inferred read-only

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、数字人） only_internal_use: 是否仅企业内部使用、不对外提供

Inferred read-only

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）。

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.savantcat-ai-compliance]
url = "https://savantcat.cn/mcp-compliance"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "savantcat-ai-compliance": {
      "type": "http",
      "url": "https://savantcat.cn/mcp-compliance"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: savantcat-ai-compliance
Remote MCP URL: https://savantcat.cn/mcp-compliance

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "savantcat-ai-compliance": {
      "url": "https://savantcat.cn/mcp-compliance"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "savantcat-ai-compliance": {
      "type": "http",
      "url": "https://savantcat.cn/mcp-compliance"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "savantcat-ai-compliance",
  "transport": "streamable-http",
  "url": "https://savantcat.cn/mcp-compliance"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 3

https://savantcat.cn/mcp-geo

No auth detected

MCP server metadata

Name: savantcat-geo-cn

Capabilities

experimentalpromptsresourcestools

Server instructions

中文 AI 可引用性（GEO/AEO）工具包：审计网站能否被 AI 搜索抓取、读懂、引用，探测问题在中文信源池中的占位，并按五大指标 + 语义角色分权输出可自验的测量报告。评分是确定性的（scoring_version 随结果返回），不做 LLM 判定。每次输出都带 _provenance 溯源块（品牌/出处/指纹/授权要求）。

Known tools 4

audit_cn_citability

审计一个网站/页面能否被中文 AI 搜索（豆包、DeepSeek、文心、Kimi 等）抓取、解析与引用。一次抓取完成六层检查：可抓取（含中国爬虫矩阵与边缘层拦截实测）、可解析、可引用、实体一致、分发、可信可自验；返回 0-100 分与 A-F 等级、逐项证据、优先修复清单。用途场景：客户站点体检、上线前自检；传 compare_with 可做竞品对比（逐层与逐项差异）。注意：只做确定性检查，不调用大模型；评分口径见 scoring_version。

Inferred read-only

probe_source_pool

探测一个中文问题在信源池里的实际占位分布，并判断你的品牌/域名是否在池子里。原理：AI 答案只能引用「已进入检索池」的来源。若目标问题下主流信源被平台型站点（知乎/公众号转载站/百家号/CSDN 等）占满而你不在其中，再好的站内优化也不会被引用。返回：结果域名分布、平台归类、是否命中你的品牌/域名、同题竞品域名清单、建议动作。参数：question 用户真实会问的问题原话；brand 品牌词（如「合尘猫」）；domain 你的域名（如 savantcat.

Inferred read-only

score_visibility

按五大核心指标 + 语义角色分权，计算 AI 搜索可见度并输出可自验的测量报告。输入 samples 为 JSON 字符串： {"brand":"合尘猫","domain":"savantcat.

Inferred read-only

plan_fixes

按缺口生成优先修复计划（可直接交给客户或工程执行）。两种用法：① 传 fail_ids（逗号分隔的自查项编号，如 "L1-3,L2-4"）；② 传 url，工具先审计再出计划。返回：按权重排序的修复项、每项「为什么」「怎么补」「验收方式」。

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.savantcat-geo-cn]
url = "https://savantcat.cn/mcp-geo"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "savantcat-geo-cn": {
      "type": "http",
      "url": "https://savantcat.cn/mcp-geo"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: savantcat-geo-cn
Remote MCP URL: https://savantcat.cn/mcp-geo

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "savantcat-geo-cn": {
      "url": "https://savantcat.cn/mcp-geo"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "savantcat-geo-cn": {
      "type": "http",
      "url": "https://savantcat.cn/mcp-geo"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "savantcat-geo-cn",
  "transport": "streamable-http",
  "url": "https://savantcat.cn/mcp-geo"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.