Community · Official remote MCP server

The 中文 AI 可引用性(GEO/AEO)体检 MCP server,
connected in one click.

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. Connect the official 中文 AI 可引用性(GEO/AEO)体检 MCP server to Claude, ChatGPT, or Cursor through gate — one gateway URL, no config files, security-checked.

Free to start · No credit card · No hosting needed

Use this server

Add 中文 AI 可引用性(GEO/AEO)体检 to your AI in one minute

Pick your client. Copy, paste, done — or let gate handle sign-ins and policies for you.

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

Run in your terminal, then restart Claude Code.

中文 AI 可引用性(GEO/AEO)体检 · https://savantcat.cn/mcp-geo

What you can do

What your AI can do with 中文 AI 可引用性(GEO/AEO)体检

Real prompts you can type the moment it's connected — no setup, no docs to read.

“Use “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.”

“Use “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.”

“Use “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.cn","baseline_negative":3,.”

“Use “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」。.”

Security check

How secure is the 中文 AI 可引用性(GEO/AEO)体检 MCP server?

Every server in the gate directory has to pass the same four checks before your AI can touch it. Here's how 中文 AI 可引用性(GEO/AEO)体检 holds up.

✓ Verified directory server中文 AI 可引用性(GEO/AEO)体检 · savantcat.cn

Official endpoint

Operated by 中文 AI 可引用性(GEO/AEO)体检 (savantcat.cn) at its documented MCP endpoint — not a third-party mirror or community re-host.

No sign-in needed

This server only exposes public data — no account and no credentials are involved when you connect.

Scanned before it goes live

gate checks every tool for prompt injection, hidden instructions, data-exfiltration hints, and over-broad permissions before the server is available through your gateway.

Watched for drift

If 中文 AI 可引用性(GEO/AEO)体检 adds or changes tools later, gate re-scans and alerts you — before your AI acts on the change.

How it works

Connected in three steps

01

Connect your gate

Add one gateway URL to Claude, ChatGPT, or any MCP client. One-time setup, about two minutes.

02

Pick 中文 AI 可引用性(GEO/AEO)体检

Choose 中文 AI 可引用性(GEO/AEO)体检 in the gate directory. No sign-in needed.

03

Use it anywhere

中文 AI 可引用性(GEO/AEO)体检's tools are live in every AI client you've connected — with rules and logging built in.

Connect 中文 AI 可引用性(GEO/AEO)体检 free

Free to start · No credit card · No hosting needed

Straight from the server

The actual tools 中文 AI 可引用性(GEO/AEO)体检 exposes

Fetched live from the official endpoint and re-checked daily by gate — not marketing copy.

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

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

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.cn","baseline_negative":3,

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」。

query_history — 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:

diff_observations — 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

list_signals — 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 limi

Author

Who runs the 中文 AI 可引用性(GEO/AEO)体检 MCP server?

Server facts

The 中文 AI 可引用性(GEO/AEO)体检 MCP server at a glance

Endpointhttps://savantcat.cn/mcp-geo
Operated by中文 AI 可引用性(GEO/AEO)体检 (savantcat.cn)
CategoryCommunity
Sign-inNone — public data only
Available in gateYes — one-click connect
Works withClaude, ChatGPT, Cursor & any MCP client
FAQ

Questions, answered

Is there an official 中文 AI 可引用性(GEO/AEO)体检 MCP server?

Yes — 中文 AI 可引用性(GEO/AEO)体检 operates its own remote MCP server at savantcat.cn. gate connects you to that official endpoint and adds security scanning, per-tool access rules, and an activity log on top.

How do I connect 中文 AI 可引用性(GEO/AEO)体检 to Claude or ChatGPT?

Add gate's gateway URL to your AI client once, then pick 中文 AI 可引用性(GEO/AEO)体检 in the directory. No account or sign-in is needed. From then on, 中文 AI 可引用性(GEO/AEO)体检's tools are available in every client you've connected to gate.

Do I need to host anything?

No. 中文 AI 可引用性(GEO/AEO)体检 runs the server, and gate is fully managed. You just connect one URL — there's nothing to install, deploy, or maintain.

Is the 中文 AI 可引用性(GEO/AEO)体检 MCP server safe to connect?

It's the vendor's official endpoint, and gate scans its tools for prompt injection and hidden instructions before it goes live, re-checks it whenever it changes, and lets you allow, block, or require approval for every single tool.

Is it free?

Yes — you can get started with gate for free and connect 中文 AI 可引用性(GEO/AEO)体检 in minutes. No credit card required.

More servers

Connect more than just 中文 AI 可引用性(GEO/AEO)体检

Every server below works through the same gateway URL — connect once, add tools anytime.

Set up 中文 AI 可引用性(GEO/AEO)体检 in: Claude · Claude Code · ChatGPT · Cursor · VS Code

Give your AI 中文 AI 可引用性(GEO/AEO)体检 — safely.

One URL. All MCPs. Full control. Free to start.

Get started free