Proofsource

co.proofsource由 proofsource.co 發布官方發布者v1.0.0更新於 Oct 24, 2026

AI visibility: which buyer questions name your brand in ChatGPT, Perplexity, Claude, AI Overviews.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取資料與分析商業與電商

概覽

AI 產生的概覽

讓助理查看 ChatGPT、Perplexity、Claude 和 Google AI 在回答買家問題時提及某品牌的頻率，並追蹤競品與被引用網站

可以做什麼
Proofsource 報告工作區內各品牌在 AI 回答中的能見度。讀取類工具先列出品牌和主題，再依引擎回傳提及率、聲量佔比、平均位置、引用佔比和情感傾向，以及被點名的競品、被引用的網站、近期變化和待修補的落差。寫入類工具可新增品牌、新增買家問題，並把某項修正標記為已上線，以便衡量其對提及率的影響。另有報告連結工具回傳可分享的報告，範例工具無需登入即可使用。
適用情境
當你希望助理檢視 AI 助理如何描述某品牌、查看它們改為推薦哪些競品，或依能見度落差排出優先順序計畫並追蹤已上線修正是否改變數據時使用。
執行需求
透過 OAuth 2.1 登入的遠端 Streamable HTTP 端點，需要 Proofsource 帳號（電子郵件加一次性驗證碼）。未宣告 API 金鑰或環境變數。寫入權限和問題數量上限取決於方案與角色；使用公司電子郵件的新帳號可獲得兩次免費掃描。
安裝前請注意
寫入類工具會變更工作區：add_brand 會啟動掃描，create_prompt 新增的問題計入方案問題上限，mark_fix_shipped 會記錄一項修正。報告連結是未公開列出但可分享的網址，應視為半公開資訊。提交的品牌網站會被該服務讀取。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Proofsource，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/co.proofsource%2Fproofsource/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": {
    "proofsource": {
      "type": "http",
      "url": "https://app.proofsource.co/v1/mcp"
    }
  }
}

README

Proofsource for Claude

Proofsource measures how AI assistants talk about your brand. It asks ChatGPT, Perplexity, Claude and Google AI Overviews the questions your buyers ask, and shows how often you are mentioned, which competitors are recommended instead, and which sources the answers cite.

This plugin connects Claude to your Proofsource workspace and adds two skills:

  • ai-visibility-audit: a sourced summary of your AI visibility, competitors, cited sources and recent changes.
  • fix-plan: a prioritized plan from your open gaps, plus tracking new buyer questions and shipped fixes (always asks first).

Install

/plugin marketplace add lcbasu/proofsource-plugins/plugin install proofsource@proofsource-plugins

Then run /mcp, pick proofsource and sign in with your Proofsource account. Try: "Is my brand mentioned in ChatGPT answers?"

Connect without the plugin

The connector URL is https://mcp.proofsource.co/mcp (OAuth 2.1; you sign in with your Proofsource email and a one-time code).

  • Claude (web or Desktop): Settings → Connectors → Add custom connector → paste the URL → Connect.

  • ChatGPT: Settings → Apps & Connectors → Advanced → turn on Developer mode → Create → paste the URL, choose OAuth.

  • Claude Code: claude mcp add --scope user --transport http proofsource https://mcp.proofsource.co/mcp, then /mcp to sign in.

  • Cursor, VS Code, Cline, Windsurf and other MCP clients: add a remote (Streamable HTTP) server with the URL above; see llms-install.md.

Also listed in the official MCP Registry as co.proofsource/proofsource (server.json).

Full guide: https://proofsource.co/docs/chatgpt-and-claude

Tools

Read: list_brands, list_topics, get_visibility, get_competitors, get_citations, get_changes, list_fix_opportunities, get_fix_verification, get_scan_status, get_report_link, see_example (works without signing in). Write (your workspace only, by your plan and role): add_brand, create_prompt, mark_fix_shipped.

New accounts with a work email get two free scans. Personal email addresses get an account without scans.

Support: https://proofsource.co/contact · Privacy: https://proofsource.co/privacy · Terms: https://proofsource.co/terms

來源：README.md，提交 a027e15

工具

14

list_brands

List my tracked brands

The brands this workspace tracks in AI answers, with ids and websites. Call first; every other tool takes a brand_id.

無需輸入參數。

list_topics

Which buyer questions are tracked?

The topics and buyer questions this workspace asks ChatGPT, Perplexity, Claude and Google AI for a brand. Gives the topic_id create_prompt needs.

輸入參數brand_id

get_visibility

Is my brand mentioned in AI answers?

How often ChatGPT, Perplexity, Claude and Google AI mention the brand when buyers ask about its category. by=engine (default): mention rate, share of voice, average position, citation share and sentiment per engine, with the change from the previous period. by=question: each buyer question's mention rate and rank.

輸入參數byenginesbrand_idwindow_days

get_competitors

Who does AI recommend instead of me?

The competitors AI answers name for the brand's buyer questions, per engine, with each one's share of voice against the brand and how it changed over the window.

輸入參數enginesbrand_idwindow_days

get_citations

Which sources do AI answers cite?

The websites AI answers cite for the brand's buyer questions, ranked by share of citations and by how many answers cite them, and where the brand's own site ranks.

輸入參數limitenginesbrand_idwindow_days

get_changes

What changed in my AI visibility?

What moved over the window: the daily mention-rate trend, how much the engines' answers changed, notable changes on competitors' websites, and new pages about the category.

輸入參數brand_idwindow_days

list_fix_opportunities

What should I fix to show up in AI answers?

The gaps that keep AI engines from citing or recommending the brand, each with its evidence and the suggested fix. Gives the gap_id mark_fix_shipped needs.

輸入參數brand_idinclude_closed

get_fix_verification

Did my fix work?

Each fix marked shipped for the brand with its mention rate before and after and a verdict: moved (beyond normal answer churn), within_noise, or awaiting_samples. Fixes marked "Not a fix" are left out; auto-detected page changes carry source auto_detected.

輸入參數limitbrand_idfix_event_id

create_prompt

Track a new buyer question

Adds a buyer question to a topic so it is asked on every engine in the plan from the next run. Counts toward the plan's question limit. Calling again with the same text returns the existing question, never a duplicate.

輸入參數text必填topic_id必填target_enginesconfirm_new_engines

mark_fix_shipped

I shipped a fix

Records that a fix shipped, against a gap_id from list_fix_opportunities or a published content_draft_id, so get_fix_verification can measure whether it moved the brand's mention rate. Calling again with the same fix and description returns the existing record.

輸入參數gap_idbrand_idshipped_atdescription必填content_draft_idacknowledge_unfilled_gaps

add_brand

Check my brand in AI answers

Start measuring a brand: does ChatGPT, Perplexity, Claude or Google AI mention it, and who does AI recommend instead? Give the brand's website (or its app store, Google Maps, YouTube or Instagram link). It reads the site, picks the buyer questions, and starts the first scan across the AI engines. Reading the site takes 1-2 minutes; if it is still running, call again with the same link and it picks up the same run, never a second one. Returns the brand_id; then use get_scan_status.

輸入參數link必填description

get_scan_status

Is my brand's scan done?

Progress of a brand's first scan after add_brand: the stage, how many AI answers are in out of how many expected, per engine, and when it should finish. Once complete, use get_visibility for the results.

輸入參數brand_id

see_example

See an example AI visibility card

Shows what Proofsource measures, without signing in: a real visibility card for one example brand (Tesla), from answers collected from ChatGPT, Perplexity, Claude and Google AI Overviews. It shows how often AI answers mention the brand, per engine, which competitors they name instead, and sample answers. Use it when someone asks whether their brand shows up in AI answers and has not signed in. It always shows the example brand; to check their own brand they sign in.

輸入參數brand

版本歷史

1
  1. v1.0.0最新Oct 13, 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。