Howseen

ai.howseen由 howseen.ai 發布官方發布者v1.0.0更新於 Oct 26, 2026

How ChatGPT, Gemini, Perplexity and Google AI name your brand, cite sources and rank rivals.

已驗證Streamable HTTP可網頁執行效率與工作流資料與分析商業與電商

概覽

AI 產生的概覽

Howseen 的遠端 MCP 伺服器讓助理查看品牌在 ChatGPT、Gemini、Perplexity 與 Google AI 回答中的表現，並據此採取行動。

可以做什麼
  • 列出帳號中追蹤的品牌，讀取整體 AI 能見度、聲量佔比、平均排名與情感傾向
  • 檢視追蹤的買家問題、競品比較、未被提及的問題缺口，以及 AI 引用的來源
  • 讀取真實 AI 回答、兩次掃描間的變化、優先行動計畫與最容易突破的頁面
  • 查看文章、GEO 分數、索引狀態與搜尋表現，以及方案配額和 API 限制
  • 管理問題與競品，標記或略過行動項目，起草、更新、發布、刪除或還原文章
  • 建立公開分享報告、立即執行掃描並提交搜尋引擎索引
適用情境
適合需要了解 AI 助理在買家問題上推薦哪些品牌、自己在哪裡缺席、應爭取在哪些頁面被收錄的行銷或 SEO 工作。也適合希望由助理起草並發布針對這些問題內容的團隊。
執行需求
遠端 Streamable HTTP 端點，無需安裝。需要 Howseen 帳號與 API 金鑰，以 Authorization Bearer 權杖傳送，金鑰在後台 Settings > API & AI assistants 建立。執行操作需要已啟用操作權限的金鑰。3 天試用期後需 Pro 或 Business 方案。
安裝前請注意
API 金鑰是有效憑證；只能把金鑰放在網址中的用戶端應把該網址當作密碼保管，外洩後在設定中撤銷。許多工具會變更帳號狀態，且僅在 confirm: true 時生效，包括將文章公開發布到已連接的 CMS、刪除文章、移除問題或競品、建立公開分享連結。起草與發布會消耗方案額度，掃描頻率受方案週期限制。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Howseen，將其新增到工作區。
  2. 連接 Authorization token 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 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/ai.howseen%2Fhowseen-mcp/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": {
    "howseen": {
      "type": "http",
      "url": "https://app.howseen.ai/api/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

Howseen MCP server

Ask Claude, ChatGPT, Cursor or Codex how your brand shows up in AI answers, and act on it, without leaving your AI assistant.

Howseen tracks which brands ChatGPT, Gemini, Perplexity, Google AI Overviews and Google AI Mode recommend on the questions your buyers ask, which sources those engines cite, and writes the content to win the spots you are missing. This repository documents its remote MCP server.

  • Server URL: https://app.howseen.ai/api/mcp (Streamable HTTP, remote, nothing to install)
  • Auth: Authorization: Bearer <your Howseen API key>
  • Docs: https://howseen.ai/mcp
  • Get a key: Howseen dashboard > Settings > API & AI assistants (3-day free trial)

Connect your AI assistant

Replace hs_live_YOUR_KEY with your key.

Claude Code

bash
claude mcp add --scope user --transport http howseen https://app.howseen.ai/api/mcp --header "Authorization: Bearer hs_live_YOUR_KEY"

Cursor (~/.cursor/mcp.json)

json
{  "mcpServers": {    "howseen": {      "url": "https://app.howseen.ai/api/mcp",      "headers": { "Authorization": "Bearer hs_live_YOUR_KEY" }    }  }}

Codex

bash
export HOWSEEN_API_KEY=hs_live_YOUR_KEYcodex mcp add howseen --url https://app.howseen.ai/api/mcp --bearer-token-env-var HOWSEEN_API_KEY

Claude.ai and ChatGPT (custom connector): these apps can only send the key inside the URL.

https://app.howseen.ai/api/mcp?key=hs_live_YOUR_KEY

Treat that URL like a password: do not share it or show it on screen, and revoke the key in Settings if it leaks.

What you can ask

  • "What is my AI visibility this month, per engine?"
  • "On which buyer questions does ChatGPT name a competitor and not us?"
  • "Which sites does AI cite when we lose? Where should we get listed first?"
  • "What changed since the last scan?"
  • "Draft an article for the question we lose the most, then publish it to our site."

Tools

Read (any key)

ToolWhat it returns
list_brandsThe brands (websites) tracked in the account
get_visibility% of AI answers that name the brand, share of voice, average position, sentiment, per engine, with the trend
list_promptsTracked buyer questions with per-question visibility, engines and cited domains
get_competitorsBrand vs competitors in AI answers, overall and per engine
get_top_sourcesDomains and URLs AI engines cite most on the brand's questions
search_responsesReal AI answers, with excerpts, brands named and cited URLs
get_action_planPrioritized actions to raise AI visibility
get_prompt_gapsQuestions where AI names a competitor but not the brand
get_easiest_winsThird-party pages cited in the answers the brand loses, ranked
get_changesWhat changed between the last two scans
suggest_promptsBuyer questions worth tracking that are not tracked yet
list_articlesArticles Howseen wrote for the brand, with status and URL
get_article_performancePublished articles with indexing status, impressions and clicks
get_usagePlan, quotas used and left, API limits

Actions (key with actions enabled; every action previews first and only applies with confirm: true)

add_prompts, archive_prompts, remove_prompts, add_competitor, remove_competitor, mark_action_done, dismiss_action, draft_article, refresh_article, publish_article, request_indexing, create_share_report, delete_article, restore_article.

publish_article sends a written article to the brand's connected site (WordPress, Shopify, Ghost, BigCommerce, webhook) or its Howseen-hosted blog.

REST API

The same data is available as a read-only JSON API:

bash
curl -H "Authorization: Bearer hs_live_YOUR_KEY" https://app.howseen.ai/api/v1/brandscurl -H "Authorization: Bearer hs_live_YOUR_KEY" "https://app.howseen.ai/api/v1/brands/BRAND_ID/visibility?from=2026-09-01&engine=chatgpt"

Pricing

The MCP server and the API are included in the Pro plan (79 € a month) and the Business plans, and in the 3-day free trial. See https://howseen.ai/pricing.

Support

Questions or issues: open an issue here or write to [email protected].

來源：README.md，提交 888389b

工具

29

list_brands

List brands

List the brands (websites) tracked in this Howseen account, with their id, name and domain. Call this first when the account may have several brands.

無需輸入參數。

get_visibility

Get AI visibility

Headline AI visibility of a brand: % of AI answers that name it, share of voice vs competitors, average position, sentiment, per engine, plus the trend over the period (one point per scan).

輸入參數tofrombrandengine

list_prompts

List tracked prompts

The buyer questions (prompts) tracked for a brand, with per-prompt visibility, share of voice, position, which engines name the brand, and which brands and domains are cited.

輸入參數tofrombrandlimitengineoffset

get_competitors

Get competitors

Compare the brand with its competitors in AI answers: visibility %, share of voice, average position and sentiment, overall and per engine.

輸入參數tofrombrandengine

get_top_sources

Get top cited sources

The domains and URLs AI engines cite most when answering the brand's buyer questions, overall and per engine. Use it to find where the brand should get listed or mentioned.

輸入參數tofrombrandlimitengineoffset

search_responses

Search AI answers

Read real AI answers collected for the brand: excerpts around the brand mention, whether the brand and which competitors were named, and the cited URLs. Filter by a word in the question or answer (query), by prompt text, and by engine.

輸入參數tofrombrandlimitqueryengineoffsetprompt

get_action_plan

Get action plan

Prioritized actions to raise the brand's AI visibility (off-page: get listed on the pages AI cites; content: answer uncovered buyer questions), ranked 20/80 like the dashboard Action plan, with steps.

輸入參數tofromlangbrandlimitengine

list_articles

List articles

Articles Howseen wrote for the brand (drafts, scheduled and published), with status, target question, GEO score and published URL.

輸入參數tofrombrandlimitoffset

get_prompt_gaps

Get prompt gaps

Tracked prompts where AI names at least one competitor but not the brand, per engine, with the competitors named and the domains cited. Sorted by search volume (when a cached figure exists) then by number of competitors named. Start here to see what to win back.

輸入參數tofrombrandlimitengineoffset

get_easiest_wins

Get easiest wins

Third-party sites and pages cited in the answers the brand loses (competitor named, brand not), ranked by how many lost answers cite them, with the matching action-plan item. Getting listed there is the shortest path back into those answers.

輸入參數tofromlangbrandlimitengineoffset

get_changes

Get changes

What changed between the last two completed scans (or since a date): prompts gained and lost, visibility delta per engine, tracked competitors newly named, and the likely causes (sources that started or stopped citing the brand).

輸入參數brandsinceengine

suggest_prompts

Suggest prompts to track

Buyer questions worth tracking that the brand does not track yet: real questions from Hacker News discussions (ranked by engagement) plus AI suggestions for the category. Returns suggestions only; use add_prompts to track some. Limited to 20 calls per day.

輸入參數brandcount

get_article_performance

Get article performance

Articles written for the brand with status, GEO score, published URL and search-engine indexing status (Google URL Inspection, Bing), plus impressions and clicks when Search Console or Bing is connected.

輸入參數tofrombrandlimitoffset

get_usage

Get plan usage

Plan, quotas used and left (prompts, competitors, articles, manual scans), next automatic scan estimate, what this API key may do, and the API rate limits. Call it before planning changes.

輸入參數brand

mark_action_done

Mark an action done

Mark an action-plan item as done (same state as the dashboard Action plan). Use the action id from get_action_plan or get_easiest_wins. Preview first; confirm: true applies.

輸入參數brandconfirmaction_id必填

dismiss_action

Dismiss an action

Dismiss an action-plan item the user does not want to do (moves it to Archived in the dashboard, out of the next best actions). Reversible in the dashboard. Preview first; confirm: true applies.

輸入參數brandconfirmaction_id必填

add_prompts

Add prompts to track

Track new buyer questions (prompts) for the brand, checked against the plan's prompt quota (the whole list is refused if it would exceed it). An archived prompt added again is restored. Preview first; confirm: true applies.

輸入參數brandtopicconfirmprompts必填

remove_prompts

Remove prompts

Stop tracking prompts and remove them from the prompt list (past scan results stay in history). Prefer archive_prompts to keep them listed. Preview first; confirm: true applies.

輸入參數brandconfirmprompts必填

archive_prompts

Archive prompts

Archive prompts: they stop being scanned (frees prompt quota) but keep their history and stay listed as archived in the dashboard, restorable. Preview first; confirm: true applies.

輸入參數brandconfirmprompts必填

add_competitor

Add a competitor

Track a competitor from a name or a website URL (resolved to name + domain like in Settings), within the competitor quota. Preview first; confirm: true applies.

輸入參數brandconfirmcompetitor必填

remove_competitor

Remove a competitor

Stop tracking a competitor (by name or domain). Past results keep it. Preview first; confirm: true applies.

輸入參數brandconfirmcompetitor必填

draft_article

Draft an article

Write a DRAFT article answering one buyer question, with the same quality pipeline as the app (brand context, sources AI cites, GEO checks). Never publishes. Uses the plan's article allowance. Preview first; confirm: true writes it (up to about a minute).

輸入參數brandconfirmquestion必填

refresh_article

Update an article with the current profile

Rewrite a WRITTEN article with the brand's current profile (offer, category, offerings, competitors) after it changed: same article id, slug, question and date, previous version kept (restorable in the app). A published article is never overwritten: the update lands in a refreshed draft. Free once per article after a profile change, otherwise uses the article allowance. Give article_id (list_articles) or the article's target question. Preview first (shows what changes and the quota impact); confirm: true rewrites it (up to about a minute).

輸入參數brandconfirmquestionarticle_id

create_share_report

Create a share report

Create a public, frozen report link (visibility, competitors, top prompts, recommendations) with the account's agency branding, like the dashboard Share button. Preview first; confirm: true creates the link.

輸入參數tofromlangbrandengineconfirm

run_scan

Run a visibility scan

Scan the brand's prompts on the AI engines now, with the same limit as the dashboard Run now button (a fresh scan at most once per brand per plan cadence: every 72h, every 24h on Business; prompts added since the last scan can be scanned alone; an unfinished scan can be continued). Preview first; confirm: true runs about 45 seconds per call.

輸入參數brandconfirm

publish_article

Publish an article

Publish a written article (e.g. a draft from draft_article) to the brand's connected CMS (WordPress, Shopify, Ghost, BigCommerce, GoHighLevel, Webflow, webhook) or hosted blog, now, or schedule it for a later date (needs Autopilot ON). Goes live publicly. Preview first; confirm: true publishes and returns the URL.

輸入參數brandconfirmplatformarticle_id必填publish_at

request_indexing

Request search-engine indexing

Submit a published article to the search engines connected for the brand: Google (sitemap re-submit through Search Console when connected with indexing), Bing (Webmaster key) or IndexNow for pages hosted by Howseen. If you publish on your own site from the API or feed, pass url (the live https address of the article on the brand's domain): Howseen records it and tracks indexing there. At most once per article every 24h. Preview first; confirm: true submits.

輸入參數urlbrandconfirmarticle_id必填

delete_article

Delete an article

Move an article (planned, draft or published) to the Trash, like the dashboard delete button: restorable with restore_article or in Howseen > Content > Trash, and its topic is not planned again. A post already live on the client's own CMS (WordPress, Shopify...) is NOT removed from the CMS: the preview says where it stays live. Always call WITHOUT confirm first and show the preview to the user; call again with confirm: true only after they approve.

輸入參數brandconfirmarticle_id必填

restore_article

Restore a deleted article

Bring back an article from the Trash (e.g. one deleted with delete_article). Preview first; confirm: true restores.

輸入參數brandconfirmarticle_id必填

版本歷史

1
  1. v1.0.0最新Oct 20, 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。