MCP server

中文 AI 可引用性（GEO/AEO）体检

cn.savantcat/geo-cn

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

中文站能否被豆包/DeepSeek/文心/Kimi 抓取、读懂、引用：可引用性审计、信源池占位探测、五大指标测量、修复计划、观测时序追踪

Working at last checkVerified publisher: savantcat.cnAbout 1,287 tokens per request once connected7 tools

Website Source

https://savantcat.cn/mcp-geo

At a glance

Type: MCP server
Publisher: savantcat.cn (verified by the MCP Registry)
Status: Working at last check
Tools: 7
Token cost: About 1,287 tokens per request
Sets up in: Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
Last checked: 26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to Cursor Add to VS Code VS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http geo-cn https://savantcat.cn/mcp-geo

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

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

Gemini CLI

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

Cursor

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

VS Code

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

Antigravity

agy mcp add geo-cn https://savantcat.cn/mcp-geo

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"geo-cn","server_url":"https://savantcat.cn/mcp-geo","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"geo-cn","server_url":"https://savantcat.cn/mcp-geo"}

Tools

audit_cn_citability ~169 tokens
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。
diff_observations ~172 tokens
对比某 identity 的**最近两次观测**，判定提升/退化/中性（带阈值与样本门槛说明）。判定门槛：相对变化 >= 20% **且** 绝对变化 >= 0.05 才算"显著"（severity: rise / sharp_drop）。样本 n < 20 一律返回 severity=low_n，**不给出升降结论**——这是防误报的硬门。 Args: identity: 品牌名或域名 kind: 观测类型，留空取全部 series: 题集/口径标识，留空取全部
list_signals ~114 tokens
列出**已检测到的变化信号**（visibility 提升/退化等），带生命周期（first_seen / resolved_at）。 Args: status: open（未解决，默认）/ resolved（已解决）/ all limit: 最多返回条数
plan_fixes ~121 tokens
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」。
probe_source_pool ~166 tokens
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.cn）。
query_history ~222 tokens
查某个品牌/域名在**历史观测**中的时序（多次采样的轨迹）。数据来自本工作室按周期采样的记录（写入走 CLI，服务本身只读）。 **只在同一 series（同一题集/同一口径）内纵向比较**，不同 series 的值不可直接比大小。 Args: identity: 品牌名或域名，如 "合尘猫" / "savantcat.cn" kind: 观测类型，留空取全部。常用：mention_rate(提及率) / citation_rate(引用率) / visibility_score(可见度分) / ran
score_visibility ~323 tokens
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.cn","baseline_negative":3, "fact_points":["服务范围","交付周期","定价方式"], "samples":[{"question":"Q1","platform":"DeepSeek","run":1,"answer":"原文回答……", "role":"independent|joi

Browse

Calling other AI models

Related MCP servers

Andreax
270 pay-per-call AI tools for agents, paid via x402 (USDC on Base). No signup, no API keys.
CCAPI
Image, video, music and text generation across 100+ models through one endpoint.
Vaaya
Paid APIs and tokenized shares for agents. Prepaid funding, including authorized Instinct checkout.
TANDIU AI infrastructure data
Free, no auth. Daily CN AI infra: LLM prices, index, trends, GPU, estimators, agents, PC, funding.
GO AI Tools
31 no-AI tools: image conversion and EXIF stripping, App Store assets, colour maths. No API key.
Anansi Haven
Free home base for AI agents: memory, job board, agent directory, safe commons and free tools.
Unifically
One API for 100+ AI video, image, music and speech models.
Kimi-K3 Abliterated Chat
Chat with Kimi-K3 Abliterated (uncensored)

Badge for your README

[![AptLynx](https://aptlynx.net/badge/cn.savantcat/geo-cn.svg)](https://aptlynx.net/servers/cn.savantcat/geo-cn)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents