中文 AI 可引用性(GEO/AEO)体检
Server Details
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
- Status
- Healthy
- Uptime
- 82.6% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- savantcat/mcp-geo-cn
- GitHub Stars
- 1
- Server Listing
- geo-cn
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
The tools mostly have distinct purposes: audit, plan fixes, probe source pool, score visibility, and query/diff/list observation data. There is some conceptual overlap among diff_observations, list_signals, and query_history because all deal with observation history/signals, but the descriptions clarify different actions and outputs.
All tool names use consistent snake_case with a verb-first pattern: audit_cn_citability, diff_observations, list_signals, plan_fixes, probe_source_pool, query_history, score_visibility. Minor length differences do not break the convention.
Seven tools is well-scoped for a GEO/AEO citability audit and visibility tracking server. Each tool covers a distinct part of the diagnostic workflow without obvious redundancy.
The surface covers audit, fix planning, source-pool probing, visibility scoring, historical queries, diffs, and signal listing, which is strong lifecycle coverage. Minor gaps exist around writing/ingesting observations or resolving signals directly, though the description notes writes happen via CLI.
Available Tools
7 toolsaudit_cn_citabilityARead-onlyIdempotentInspect
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。
Inputs: url (required), include_raw, compare_with. Returns: result
diff_observationsARead-onlyIdempotentInspect
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
Inputs: identity (required), kind, series. Returns: result
list_signalsBRead-onlyIdempotentInspect
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
Inputs: limit, status. Returns: result
plan_fixesARead-onlyIdempotentInspect
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」。
Inputs: top, url, fail_ids. Returns: result
probe_source_poolARead-onlyIdempotentInspect
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)。
Inputs: question (required), brand, domain. Returns: result
query_historyARead-onlyIdempotentInspect
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) / rank(排名) / robots_policy / llms_txt
series: 题集/口径标识,留空取全部
limit: 每条 series 最多返回的最新点数
Inputs: identity (required), kind, limit, series. Returns: result
score_visibilityARead-onlyIdempotentInspect
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|joint|citation_only|none",
"sentiment":"positive|neutral|negative",
"facts":"accurate|partial|wrong|unverifiable",
"facts_found":["服务范围"],"as_of":"2026-09-19"}]}
口径:每题建议多轮(同一问题重复 7-8 次);role 分级对应语义角色权重;
返回五大指标、语义角色加权分、逐题明细与「原文摘录」(便于客户自验)。
verify_citations=True 时会实测 AI 回答里引用的 URL 是否真的可访问(幻觉守卫);
extract_claims=True 时会把回答中的数字声明单独列出并标记为未核验。
Inputs: samples (required), extract_claims, verify_citations. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Free AI-readiness audit: can ChatGPT, Claude and Perplexity read and cite a site? Fix snippets.
Live 62-rule SEO, AEO & GEO audit, RFC 9727 api-catalog, llms.txt & AI citation tools.
6-category AI readiness, Schema.org, robots.txt, /llms.txt & 25k-token audit + auto-fix MCP server
Measure how AI engines cite your brand. Cross-engine GEO visibility, as agent tools.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceAI 可见性审计(中文版):多模型询问 ChatGPT/Perplexity/Grok 对品牌的真实认知,扫描 GEO/SEO 健康度,返回 0-100 评分和基准分位。MIT
- AlicenseAqualityDmaintenanceAudits AI-bot visibility: robots.txt per-bot for 22 AI user-agents (GPTBot/ClaudeBot/PerplexityBot/etc), Cloudflare flags, JSON-LD, sitemap, llms.txt, SPA shell, plus cross-model brand mentions via Perplexity + OpenRouter. 0-100 score. SSRF-guarded, spend-capped.41MIT
- AlicenseNot gradedqualityDmaintenanceEnables auditing AI search visibility: checks site readiness for AI crawlers and measures whether ChatGPT, Gemini, and Perplexity recommend your site, including verbatim answers and citation gap analysis.4AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceA remote Model Context Protocol server developed by Inxy.ai that lets any AI agent — Claude, ChatGPT, Cursor, and others — audit a website or Shopify store for AEO / GEO / LLMO readiness: how likely ChatGPT, Claude, Perplexity, and Google AI are to cite it.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.