whereamimentioned

com.whereamimentioned由 whereamimentioned.com 發布官方發布者v0.1.0-rc.1更新於 Nov 7, 2026

Measure whether AI assistants mention your brand. Reports, model answers, scans, free site tools.

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

稽核網站的 AI 可發現性（robots.txt 爬蟲規則、llms.txt、網站地圖、結構化資料、分塊、中繼描述），並可憑 API 金鑰讀取品牌提及掃描與報告。

可以做什麼
  • 檢查 robots.txt 中允許或封鎖各 AI 爬蟲的規則及判定行
  • 爬取網站以驗證或產生 llms.txt 與 llms-full.txt
  • 爬取網站並回傳 sitemap.xml
  • 驗證 JSON-LD 結構化資料，並統計 microdata 與 RDFa 標註數量
  • 評估頁面對檢索的分塊品質，分析標題、中繼描述與開頭段落
  • 憑 API 金鑰讀取組織的掃描、報告與提示詞，並啟動掃描
適用情境
適合讓助理評估網站在 AI 助理面前的可發現性與可引用性，或產生 llms.txt 與網站地圖檔案。帳戶類工具適合已付費使用 whereamimentioned、希望在聊天用戶端中查看掃描結果與報告的團隊。
執行需求
遠端 streamable HTTP 端點，不需本機執行環境。網站工具不需憑證。帳戶工具需要組織設定頁中的 API 金鑰，透過 Authorization 的 Bearer 標頭傳送。啟動掃描會消耗額度，estimate_scan 免費並回傳 run_scan 所需的報價。
安裝前請注意
Authorization 標頭攜帶付費組織帳戶的 API 金鑰。啟動掃描會消耗額度，建議先查看免費估價。帳戶工具會讀取組織的掃描、報告與提示詞。網站工具會爬取目標網站，且所有請求都送往廠商的託管服務。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 whereamimentioned，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/com.whereamimentioned%2Fwhereamimentioned/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": {
    "whereamimentioned": {
      "type": "http",
      "url": "https://whereamimentioned.com/api/mcp"
    }
  }
}

README

whereamimentioned packages

This repository is generated. It is a one-way copy of the packages/ directory of a private repository, rebuilt from scratch and force-pushed on every release tag. Nothing here is edited by hand: a commit made in this repository is destroyed by the next sync, with no warning and no merge, and a pull request opened here is opened against a copy of a file its author cannot reach and will be destroyed the same way. Please do not send pull requests to this repository. The root package.json, vitest.config.mts and pnpm-lock.yaml are generated by the same sync and exist only so that this tree installs, typechecks, tests and builds on its own.

What is here

Three npm packages, versioned and released together, for whereamimentioned, which measures whether AI assistants mention your brand.

  • packages/cli, published as @whereamimentioned/cli. The wam command line: the free site checks that need no account, scans and reports from a terminal or from CI, and the installer for the MCP server. Documented at whereamimentioned.com/docs/cli.
  • packages/mcp-stdio, published as @whereamimentioned/mcp. A small stdio bridge for MCP clients that cannot add a remote URL. It forwards each request to the hosted server at https://whereamimentioned.com/api/mcp and holds no tool definitions of its own. Documented at whereamimentioned.com/docs/mcp.
  • packages/api-client, published as @whereamimentioned/api-client. The typed client and response types for the REST API at https://whereamimentioned.com/api/v1, described by its OpenAPI document. The other two packages are built against it.

None of the three contains server code, database access or a secret. Every request they make goes to https://whereamimentioned.com.

Releases

Releases run from this repository so that npm provenance and GitHub artifact attestations are generated. Each release tag (cli-v*) carries a GitHub Release with the CLI tarball and a SHA256SUMS file, and the npm packages carry provenance pointing back here.

Reporting a problem

Open an issue in this repository's issue tracker. Issues are not part of the synced tree, so they survive the sync; pull requests do not. For anything involving your account or your data, use whereamimentioned.com/contact instead of a public issue.

來源：README.md，提交 89823cf

工具

7

check_ai_crawler_access

Check AI crawler access

Check whether a site's robots.txt allows or blocks each known AI crawler (GPTBot, ClaudeBot, PerplexityBot, Google-Extended and about thirty others), with the exact rule and line that decided it.

輸入參數url必填

validate_llms_txt

Validate llms.txt

Fetch and validate a site's llms.txt: findings with severity and line numbers, a 0 to 100 score, section and entry counts, whether the linked URLs resolve, and whether a sibling llms-full.txt exists.

輸入參數url必填

generate_llms_txt

Generate llms.txt

Crawl a site and generate an llms.txt. depth "index" produces the link index (up to 30 pages); depth "full" produces llms-full.txt with extracted page content (up to 20 pages).

輸入參數url必填depthsiteNamedescription

generate_sitemap

Generate sitemap

Crawl a site (up to 200 pages, sitemap-first with a link-following fallback) and return a valid sitemap.xml, with lastmod only where it was genuinely observed.

輸入參數url必填

analyze_content_chunking

Analyze content chunking

Analyze how well a page is chunked for retrieval: per-heading sections with word and token counts, findings by severity, strengths, a score and the top fixes.

輸入參數url必填

validate_structured_data

Validate structured data

Fetch a page, validate its JSON-LD entities against the schema.org types that matter for AI visibility, and report per-entity findings with severity, entity counts and a score. Also reports how many microdata and RDFa annotations are present, without validating them.

輸入參數url必填

check_meta_description

Check meta description

Analyze a page's title, meta description, og:description and opening paragraph: character and pixel widths, where desktop and mobile truncate, a score and per-check findings.

輸入參數url必填keyword

版本歷史

1
  1. v0.1.0-rc.1最新Nov 7, 2026

評分

已滿足適用檢查項的 90%

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

    請在儲存庫或註冊中心條目中宣告授權條款。