FactoGraph

app.factograph由 factograph.app 發布官方發布者v0.2.0更新於 Oct 26, 2026

Memory for AI agents: facts a person approved, each with a link, and answers that cite them.

已驗證Streamable HTTP可網頁執行知識與記憶AI 與機器學習

概覽

AI 產生的概覽

FactoGraph 是給 AI 代理用的遠端記憶庫:保存經本人確認的事實,並只依這些事實回答問題,每項論述都連回對應事實。

可以做什麼
  • 閱讀儲存庫的使用手冊,了解其中有多少事實、來自哪些來源
  • 列出庫中所有事實,逐條編號,每個編號連到該事實
  • 提出問題,僅依庫中事實作答,每項論述都附連結並經過核對
  • 執行 propose、add、documents、ask、remove 等步驟,並查詢執行中步驟的下一個提示或結果
  • 回答步驟正在等待的提示,直到步驟完成或失敗
  • 建立一個空的私有儲存庫並取得其私有連結
適用情境
適合代理需要長期保存可引用、經本人確認的事實,或回答必須以某個特定精選儲存庫為依據而非一般知識的情況。也適合要求每項論述都能回溯到已存事實的工作流程。
執行需求
遠端 streamable HTTP 端點,不需安裝套件。未宣告驗證、環境變數或標頭。每個儲存庫透過其私有連結存取,工具以 store 參數接收該連結。
安裝前請注意
儲存庫連結就是它的鑰匙:只交給本人一次,切勿放在任何公開位置。步驟可以新增或刪除事實;add 只應存入本人已確認的事實,remove 僅在 confirm 為 true 且本人同意後才刪除。須在本人同意後才建立儲存庫。連結首次開啟前不會儲存任何內容。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 FactoGraph,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/app.factograph%2Ffactograph/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": {
    "factograph": {
      "type": "http",
      "url": "https://api.factograph.app/api/mcp"
    }
  }
}

工具

7

getManual

Read a store's manual

The store's manual - how to run its steps and cite its facts - and what it holds: how many facts, from which sources. Read it before the store's other tools, and follow it.

輸入參數store

listFacts

List every fact

Every fact in the store, numbered, each number a link to the fact. Cite a fact as its number with its link, [F3](<link>).

輸入參數store

ask

Ask a store

Ask a question; the store answers only from its facts, each claim linked to its fact, and checks the answer against them. Stores nothing. Returns the step's state: `waiting` (a prompt to do and answer with replyToPrompt), `running` (call getStep), `done` (do what `next` says) or `failed`.

輸入參數storequestion必填

startStep

Start a step in the person's store

Start a step - propose, add, documents, ask or remove - in a private store, with its JSON body, as the manual says. propose stores nothing; add stores only facts the person approved, with propose's proposal_id and their reply as confirmation; remove deletes only with confirm true, after the person confirmed. Returns the step's state: `waiting` (a prompt to do and answer with replyToPrompt), `running` (call getStep), `done` (do what `next` says) or `failed`.

輸入參數body必填step必填store必填

getStep

Follow a step

Where a running step is now: its next prompt, or its result.

輸入參數storerun_id必填

replyToPrompt

Answer a step's prompt

Answer the prompt a step is waiting on - do the model work in its `system` and `messages` first. Keep answering until the step is done or failed.

輸入參數reply必填storerun_id必填call_id必填

createStore

Make a store for the person

A new, empty FactoGraph store of the person's own: its private link, which these tools take as `store`. Only after the person said yes to having one. Nothing is stored until the link is first opened. The link is the store's key: give it to them once, and never put it anywhere public.

輸入參數person_agreed必填

版本歷史

1
  1. v0.2.0最新Oct 21, 2026

評分

已滿足適用檢查項的 83%

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

    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。