AEO Scanner

io.github.Convrgent由 GitHub 帳號 Convrgent 發布v2.2.1更新於 Oct 24, 2026

AI visibility for ChatGPT/Perplexity/Claude — triple score (AEO+GEO+Agent) with fix code. Free.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取開發者工具資料與分析

概覽

AI 產生的概覽

遠端或本機執行的 MCP 伺服器，掃描網站的 AI 搜尋可見度，回傳 AEO、GEO 與 Agent Readiness 三項評分、稽核結果和修正程式碼。

可以做什麼
免費掃描網站，取得三項 0-100 評分、AI 身分卡、提及就緒度和自動辨識的業務類型及主要問題。執行付費的完整稽核，涵蓋 12 個類別並提供逐項問題與建議。並排比較兩個網站，找出競爭差距和各類別勝出方。為可見度問題產生修正程式碼（結構化資料、robots.txt、網站地圖、llms.txt、中繼標籤等）並預估評分變化。
適用情境
適合需要檢查或改善網站在 AI 搜尋引擎和代理程式中的可尋性、可引用性和可互動性，與競爭對手做基準比較，或取得具體修正程式碼的情境。
執行需求
使用遠端 HTTP 端點，或以 uvx 執行本機 PyPI 套件（stdio）。免費掃描無需驗證。付費工具需要 AEO_API_KEY 環境變數，或透過 Base 網路上的 x402 協定按次以 USDC 付款。需要能連線到被掃描網站的網路。
安裝前請注意
付費工具（稽核、比較、修正）按次收費（1、3、5 美元），需要 API 金鑰或加密貨幣付款，金鑰應保密。服務會擷取目標網站並將其內容傳送到第三方伺服器。免費掃描依 IP 和依 URL 有頻率限制。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 AEO Scanner，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.Convrgent%2Faeo-scanner/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "aeo-scanner": {
      "type": "http",
      "url": "https://aeo-mcp.convrgent.ai/mcp"
    }
  }
}

README

AEO Scanner — MCP Server

AI search visibility audit for any website. Three scores, one scan.

What it does

  • AEO Score (0-100): How well AI search engines (ChatGPT, Perplexity, Google AI Overviews) can find, read, and cite your content
  • GEO Score (0-100): How likely AI is to cite your site as a source — citation readiness for AI-generated answers
  • Agent Readiness (0-100): How easily AI agents can understand, interact with, and transact on your site
  • Mention Readiness (0-100): Predicts how likely AI will mention your brand, based on 12 research-backed signals
  • AI Identity Card: How AI currently perceives your brand — gaps, citable claims, detected competitors
  • Business Profile: Auto-detected business type (commerce/saas/media/general) with which scores matter most

Quick start

Remote server (recommended) — zero install, just add the URL:

bash
# Claude Codeclaude mcp add --transport http aeo-scanner https://aeo-mcp.convrgent.ai/mcp
# Claude Desktop / Claude.ai# Settings → Connectors → Add custom connector → https://aeo-mcp.convrgent.ai/mcp
# Cursor — add to .cursor/mcp.json{ "aeo-scanner": { "url": "https://aeo-mcp.convrgent.ai/mcp" } }

Then ask your AI assistant: "Scan example.com for AI visibility"

Alternative: local install via PyPI (stdio transport):

bash
claude mcp add aeo-scanner -- uvx aeo-scanner

Tools

ToolWhat it doesPrice
scan_siteQuick triple-score scan + AI Identity Card + mention readiness + business profile + top issuesFree
audit_siteFull 58+ check breakdown across 12 categories (4 AEO + 4 GEO + 4 Agent)$1.00
compare_sitesTwo-site gap analysis + category winners + overtake fix code$3.00
fix_siteGenerated fix code with two-tier score projections — apply directly with Claude Code$5.00

Free tier

scan_site works without any authentication. No API key, no wallet, no setup.

Rate limits: 20 scans/hour per IP, 5 per URL per day.

Paid tools

audit_site, compare_sites, and fix_site require an API key:

  1. Get your key at scan.convrgent.ai
  2. Set AEO_API_KEY in your MCP config

Or pay per call with USDC via x402 protocol (Base network).

Workflow

The included optimize_site prompt guides the full workflow:

  1. Scan — get baseline scores + mention readiness + business profile (free)
  2. Compare — benchmark against detected competitors ($3)
  3. Audit — see detailed breakdown by category ($1)
  4. Fix — get working code with quick-win and full-ceiling projections ($5)
  5. Rescan — verify improvement across all scores (free)

Scoring

58+ checks across 12 categories. See the built-in aeo://reference/scoring-methodology resource for full details.

AEO categories: Structured Data (30%), Meta & Technical (20%), AI Accessibility (25%), Content Quality (25%)

GEO categories: Brand Narrative Clarity (25%), Citation Readiness (25%), Authority Signals (25%), Entity Definition (25%)

Agent Readiness categories: Machine Identity (30%), API Discoverability (25%), Structured Actions (25%), Programmatic Access (20%)

Grades: A (90+), B (75-89), C (60-74), D (40-59), F (0-39)

Research basis

GEO checks are backed by peer-reviewed research: Princeton KDD 2024 (+115% visibility from citing sources), Growth Memo (44.2% citations from first 30% of content), Cornell (+28% from quantitative claims), and more. See scoring methodology for full citations.

Built by Convrgent — AI visibility tools for agents.

來源：README.md，提交 46c902f

工具

4

scan_site

Quick AI visibility scan. Returns three scores: AEO Score (0-100, AI search engine findability), GEO Score (0-100, AI citation readiness), and Agent Readiness Score (0-100, AI agent interaction capability). Also returns AI Identity Card with mention readiness (0-100, predicts how likely AI will mention the brand), detected competitors, business profile (commerce/saas/media/general), and top 5 issues. 77+ checks across 12 categories. Free — no API key needed. Does NOT return per-check details or fix code — use audit_site for full breakdown, fix_site for generated fixes, compare_sites to benchmark against a competitor.

輸入參數url必填pages

audit_site

Full AI visibility audit across 77+ checks in 12 categories (4 AEO + 4 GEO + 4 Agent Readiness). Returns detailed per-check scores with specific issues and recommendations, AI Identity Card with mention readiness and detected competitors, and business profile. GEO checks include 3 research-backed citation signals: factual density, answer frontloading, and source citations. Agent Readiness covers emerging agent-discovery standards Cloudflare's isitagentready.com evaluates: RFC 9727 api-catalog, SEP-1649 MCP Server Card, and IETF Content-Signal (draft-romm-aipref). Does NOT generate fix code — pass this response's id as scan_id to fix_site (within 1 hour) to get fixes WITHOUT a re-crawl, or use compare_sites to benchmark against a competitor. Pay per call ($1.00) via x402 — USDC on Base or Solana. Machine payment via signed X-PAYMENT header; see https://www.x402.org/. On payment_required, the response includes the full x402 payload with payTo/amount/asset.

輸入參數url必填pagescategories

fix_site

Generate complete fix code for all AI visibility issues across AEO, GEO, and Agent Readiness. Returns working code you can apply directly — schema generation, robots.txt, sitemap, llms.txt, meta tags, structured data, citation signals, entity markup. Also returns two-tier score projections: quick wins (critical + high fixes only) and full implementation ceiling (all fixes). TIP: pass scan_id from a fresh audit_site result (kept 1 hour) to skip the re-crawl — instant response, same price. Content recommendations include research citations. Run scan_site first to see which issues exist. Pay per call ($5.00) via x402 — USDC on Base or Solana. On payment_required, the response includes the full x402 payload with payTo/amount/asset.

輸入參數urlpagesformatscan_id

compare_sites

Competitive gap analysis — scans two sites concurrently, shows side-by-side scores, category-by-category winners, competitive gaps (checks where the competitor scored 20+ higher), and generated overtake fix code with projected scores after closing gaps. Use this when the user wants to benchmark against a competitor or when scan_site detects competitors in the AI Identity Card. Pay per call ($3.00) via x402 — USDC on Base or Solana. On payment_required, the response includes the full x402 payload with payTo/amount/asset.

輸入參數url必填pagescompetitorUrl必填

版本歷史

1
  1. v2.2.1最新Sep 16, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分