INDIVIDUAL MCP TOOL

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。

savantcat.cnnone authenticationAvailability not checked

LIVE ENDPOINT

https://savantcat.cn/mcp-geo

No auth detected

Connect to this endpoint to inspect the live schema for audit_cn_citability and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

savantcat.cn

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.

Related tools

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.
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.
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」。