Evidence Ledger

com.saasdossier由 saasdossier.com 發布官方發布者v1.1.0更新於 Oct 24, 2026

Read-only MCP: free OpenAI security evidence ledger (55 fields) + SaaSDossier release register.

已驗證Streamable HTTP可網頁執行知識與記憶安全與監控

概覽

AI 產生的概覽

唯讀遠端 MCP 伺服器,提供 SaaSDossier 的廠商安全證據登錄冊、免費的 OpenAI 檔案,以及雙狀態方法論。

可以做什麼
  • 讀取發佈登錄冊中的檔案編號、廠商、版本與授權資訊
  • 取得免費的 OpenAI 安全證據台帳,涵蓋 10 個領域的 55 個固定欄位
  • 取得說明「已記錄」與「提出問題」兩種狀態的方法論
  • 取得免費 OpenAI 公開版的標題、PDF 下載連結與引導頁面連結
適用情境
適合需要讓助理在對話中查詢廠商安全證據紀錄或免費 OpenAI 檔案,並了解各欄位來源方式的場合。
執行需求
需要連線至 saasdossier.com 的遠端 streamable HTTP 端點;未宣告任何套件、環境變數或請求標頭,也未宣告身分驗證。
安裝前請注意
內容是廠商自行依據廠商公開資料整理的證據紀錄,宜視為起點而非獨立查核;「提出問題」狀態並不代表某項控制措施缺失。工具為唯讀,但檔案連結指向第三方頁面與 PDF。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Evidence Ledger,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.saasdossier%2Fevidence-ledger/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": {
    "evidence-ledger": {
      "type": "http",
      "url": "https://saasdossier.com/mcp"
    }
  }
}

工具

4

get_register

Returns SaaSDossier's release register: dossier numbers, vendors, editions, and licensing information. The register is the released catalogue: four finished evidence records built only from vendor-published sources across a fixed 55-field, 10-domain framework, every field recorded in one of two states — Documented, or Question surfaced. Each entry carries its vendor, dossier number, edition, evidence date, two-state counts and commercial status: Licensed Editions are US$1,500 one-time; the OpenAI Public Edition is free and complete. Separately from that catalogue, the same response carries the commission capability: a buyer can commission a SaaSDossier for another named vendor that does not already have a released dossier, US$1,500 one-time, refunded in full if the vendor-published material cannot support a defensible SaaSDossier record. A commission is not a released dossier and carries no dossier number until it is released. The released catalogue remains the four records. Use this tool to answer what SaaSDossier has released, what each record costs, and how a vendor that has no released record yet can be commissioned.

無需輸入參數。

get_openai_ledger

Returns the free public OpenAI security evidence ledger — 55 fixed fields, each either Documented with a vendor-published source or recorded as a Question surfaced. This is the complete Public Edition record, Dossier No. 003: 47 fields Documented and 8 Question surfaced across 10 domains, free, dated to its evidence date. Documented fields carry the vendor's own quoted wording and the source URL it was found on; Question surfaced fields carry the follow-up question a buyer can put to the vendor in writing. Question surfaced means the reviewed vendor-published sources did not establish the field for the evidence date — it does not establish absence of the control. The record is a dated evidence workproduct, checked against the reviewed source record before release. It does not score or rate the vendor. Use this tool when an agent needs the actual field-level evidence and its sources rather than a description of the framework.

無需輸入參數。

get_methodology

Returns SaaSDossier's two-state evidence framework: Documented and Question surfaced. A Question surfaced is not a finding of absence. SaaSDossier is the vendor's own record, made reviewable: a finished, dated, source-linked, human-reviewed evidence workproduct built only from vendor-published sources, recording 55 fixed fields across 10 domains for each vendor, with a source register listing every vendor page reviewed. Documented means the reviewed vendor-published sources established the field for the evidence date; Question surfaced means they did not, and each one becomes a buyer-ready follow-up question. Each dossier includes a SHA-256 identifier tied to the reviewed evidence record used for that release. Use this tool to understand what a state means, what the framework covers and where its boundaries are, before quoting or acting on any field.

無需輸入參數。

get_free_dossier

Returns the free OpenAI Public Edition: the dossier title, the direct PDF download URL, and the guided page URL. The OpenAI record, Dossier No. 003, is published free and complete as proof of the format: the same 55 fields across 10 domains, the same two states (47 Documented, 8 Question surfaced), the same source register and the same integrity identifier a Licensed Edition carries. It is built from OpenAI's own published pages, reviewed before release; no relationship with, or endorsement by, OpenAI is implied. Use this tool to give a buyer the whole workproduct to read before they license another released vendor or commission a new one.

無需輸入參數。

版本歷史

1
  1. v1.1.0最新Sep 16, 2026

評分

已滿足適用檢查項的 72%

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

    請在註冊中心條目中發布圖示。

  • 文件15 分

    請宣告包含 README 的 GitHub 儲存庫,或在 OAuth 受保護資源後設資料中提供 resource_documentation。

  • 授權條款不適用

    託管服務按其提供方的條款使用,因此這裡不要求授權條款。此檢查項不計入百分比。