FRESH — Shared URL Freshness Intelligence

io.github.GSterlingPress由 GitHub 帳號 GSterlingPress 發布v0.1.3更新於 Oct 25, 2026

Decide whether an agent should reuse cached URL knowledge or fetch the resource again.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取知識與記憶

概覽

AI 產生的概覽

一個遠端 MCP 服務，用來判斷先前看過的網址是否可能仍夠新、可以重複使用，還是應該重新抓取。

可以做什麼
在再次取得某個網址前先查詢，依據共享的變更歷史與容忍時間窗回傳 REUSE、REFETCH 或 UNKNOWN 決策。在完成一次取得後回報新鮮度證據，例如時間戳、ETag、Last-Modified 與內容雜湊，以充實共享歷史。決策偏保守：證據不足時回傳 UNKNOWN。
適用情境
適合會快取或嵌入網頁內容的助理，用來避免重複抓取、重新爬取、重新轉譯或重新嵌入可能未變動的頁面。最適合反覆造訪同一批網址、希望在真正發起取得前先做低成本判斷的工作流程。
執行需求
需要遠端 streamable HTTP 端點；未宣告本機套件、帳號、API 金鑰或環境變數。需要能連線到該託管服務的網路。查詢呼叫需要網址、上次看到的時間與容忍秒數；回報呼叫需要網址、觀測時間以及選用的 ETag、Last-Modified 與內容雜湊。
安裝前請注意
此服務自述為早期版本的實驗性生產基礎設施，決策可能不可靠。送出的網址會以單向雜湊連同彙總觀測中繼資料保存，託管方仍能得知哪些網址被查詢。不要傳送原始頁面內容、Cookie、目標網站憑證或客戶資料；服務表示並不需要這些。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 FRESH — Shared URL Freshness Intelligence，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/io.github.GSterlingPress%2Ffresh/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": {
    "fresh-shared-url-freshness-intelligence": {
      "type": "http",
      "url": "https://fresh-api-production-c783.up.railway.app/mcp"
    }
  }
}

README

FRESH

Know whether to fetch again.

FRESH is shared URL freshness intelligence for AI agents. Before re-fetching, re-scraping, re-rendering, or re-embedding a URL, ask whether the previously seen version is probably still fresh enough to reuse.

Production base URL: https://fresh-api-production-c783.up.railway.app

MCP endpoint: https://fresh-api-production-c783.up.railway.app/mcp

FRESH returns one of three decisions:

  • REUSE — cached knowledge is probably still fresh enough
  • REFETCH — the URL is likely stale enough to justify another retrieval
  • UNKNOWN — evidence is insufficient; FRESH prefers uncertainty over false confidence

Why FRESH exists

A local cache knows when you last fetched something. It does not know whether the outside resource changed since then, nor what other callers recently observed. FRESH builds shared, privacy-safe URL change history from timestamps, ETags, Last-Modified values, and content hashes.

REST

POST /v1/check

json
{"url":"https://example.com/docs/api","lastSeenAt":"2026-08-13T12:00:00Z","toleranceSeconds":3600}

POST /v1/observe

json
{"url":"https://example.com/docs/api","observedAt":"2026-08-13T13:00:00Z","etag":"abc123","lastModified":"Wed, 13 Aug 2026 12:45:00 GMT","contentHash":"sha256:..."}

Raw page content is not required.

MCP

  • fresh_check — decide whether to retrieve a URL again
  • fresh_observe — report privacy-safe freshness evidence after retrieval

Privacy

FRESH does not need raw page contents, cookies, target-site credentials, or customer payloads. URL keys are stored as one-way hashes with aggregate observation metadata.

Stranger verification

A core-tool invocation is evidence of use, not automatically proof of a genuine stranger. FRESH classifies candidate activity as KNOWN_VALIDATOR, LIKELY_VALIDATOR, CONTROLLED_TEST, UNKNOWN_MACHINE, or CREDIBLE_REAL_USE. Only CREDIBLE_REAL_USE advances stranger milestones.

Our acceptance/smoke traffic uses X-Tollbooth-Internal: 1 or X-Fresh-Internal: 1 so it cannot earn stranger credit.

Production acceptance gate

Every Railway deployment now performs live internal checks against the running service before /health can return 200. The gate exercises REST, UNKNOWN, REUSE, REFETCH, persistent observation reload, MCP initialize, MCP tool discovery, MCP fresh_check, and verifies that the controlled self-test does not increase the verified-stranger count.

Status

v0.1.2 experimental production infrastructure. Priorities: conservative decisions, low latency, sub-penny economics, privacy-safe shared learning, REST + MCP, durable observations, and auditable real-use analytics.

來源：README.md，提交 12137c0

工具

2

fresh_check

Should I Fetch This URL Again?

Return REUSE, REFETCH, or UNKNOWN before retrieving a URL again.

輸入參數url必填lastSeenAt必填toleranceSeconds

fresh_observe

Report URL Observation

Report privacy-safe freshness metadata from a completed retrieval.

輸入參數url必填etagobservedAtcontentHashlastModified

版本歷史

1
  1. v0.1.3最新Sep 16, 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。