Search Fragments

com.searchfragments由 searchfragments.com 發布官方發布者v0.2.5更新於 Oct 24, 2026

Pieces together films, shows, songs, books, quotes, places and studies from remembered fragments.

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

遠端 MCP 伺服器,可依零碎記憶找出電影、影集、歌曲、書籍、名言、地點與研究,並查核事實陳述。

可以做什麼
  • 解析片段:依場景、台詞、大約年代等記憶線索,找出電影、影集、歌曲、書籍、遊戲、名言、人物、地點、事件或研究
  • 查核陳述:對照目前網路來源檢驗具體事實主張,回傳附引用證據與明確限制的結論
  • 提交回饋:將解析結果標記為接受、部分符合或否定,或從候選清單中挑選項目
  • 結果以明確答案、排序候選清單或明確的「無法解析」三種形式回傳
適用情境
適合使用者只記得零碎線索、說不清是什麼的情況,或需要對照來源核實某項具體事實主張時。不適合眾所皆知的事實,這類情況一般搜尋更快。
執行需求
遠端 streamable-HTTP 端點,無需本機安裝。基本免費使用不需註冊或驗證;需要驗證時可使用 OAuth 2.0(授權碼 + PKCE)。需要能連線至該託管服務的網路。
安裝前請注意
查詢內容與回饋會傳送給第三方託管服務,傳送敏感資訊前請先查看其隱私政策。回饋工具會記錄解析是否正確,並由服務方保存。對陳述的結論依據來源,可能僅部分支持或無法下定論。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Search Fragments,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.searchfragments%2Fsearch-fragments/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": {
    "search-fragments": {
      "type": "http",
      "url": "https://searchfragments.com/api/mcp"
    }
  }
}

README

Search Fragments

Resolve half-remembered queries without guessing. A confident answer, a ranked shortlist, or an honest no. For when you half-remember something and can't place it. Half-remembered, cross-source queries usually take a dozen tabs and five rephrasings; Search Fragments collapses that into one call. Not for well-known facts, where normal search is faster.

Tools: resolve_fragment, verify_claim, submit_resolution_feedback Free. No signup required.

Available in Claude, Cursor, Raycast and GitHub, or add the URL below to any MCP-compatible agent.

json
{  "mcpServers": {    "search-fragments": {      "url": "https://searchfragments.com/api/mcp"    }  }}

Why this exists

AI agents tend to become confidently wrong on fragmented queries: partial memories, indirect relationships, missing names. There's real signal in the fragment — enough for a model to recognize the pattern — but not enough to verify an answer from memory alone. The result is fluent, specific, and wrong.

Search Fragments is built to decline rather than guess. Every query resolves to one of three honest shapes:

  • Resolved — a named answer, with confidence backed by evidence found.
  • Weighted Partial — a ranked shortlist of candidates to decide by eye.
  • No Resolution — an explicit "not resolvable from these clues," with no confidence claimed.

In a test against a baseline agent on 50 hard, under-documented fragments, the baseline fabricated three specific wrong answers with no hedge — Search Fragments declined honestly on all three. Full write-up: searchfragments.com/agent-hallucinations.

More on the design philosophy: searchfragments.com/why.

Server details

TypeRemote, streamable-http MCP server
Endpointhttps://searchfragments.com/api/mcp
Toolsresolve_fragment (resolve a fragment), verify_claim (check a specific claim), submit_resolution_feedback (report whether a resolution was right)
AuthNone required for basic use (free tier). OAuth 2.0 (Authorization Code + PKCE) available for authenticated use.
RegistryMCP Registry — com.searchfragments/search-fragments

See server.json for the full MCP registry manifest.

Links

License

MIT. See LICENSE.

About this repository

This repository documents and points to the hosted Search Fragments MCP server. The server itself runs as a managed remote service — there's no local install; connect to the endpoint above from any MCP-compatible client.

來源:README.md,提交 11f4a6c

工具

3

resolve_fragment

Resolve Fragment

Pieces together the name of a film, TV or radio show, song, book, game, quote, person, place, event or research study from the fragments a user remembers: a scene, a line, a face, roughly when. Pass every fragment in the user's own words, even uncertain ones. It searches many sources and fits them together. A shortlist or an honest "can't place it" is still useful. Use it when your own search couldn't place it. Not for known titles, trivia, recommendations or checking claims (use verify_claim). When the user says whether this helped, report it with submit_resolution_feedback.

輸入參數fragment必填

submit_resolution_feedback

Submit Resolution Feedback

After the user reacts to a resolve_fragment result, call this with its resolution_id. accepted: it is what they meant. partial: it helped but is not quite it. rejected: it is not what they meant. If they recognised an item in the shortlist or leads, send picked_rank (1 = first item) or picked_url; if nothing fitted, send none_fitted: true. corrected_target and new_clue are optional and are stored as feedback only; they never change graph facts.

輸入參數notestatus必填new_cluepicked_urlnone_fittedpicked_rankresolution_id必填corrected_target

verify_claim

Verify Claim

Checks whether current web sources support a specific factual assertion. Takes a claim as a natural-language statement; returns a verdict with cited evidence and stated limits. Verdict set: - "supported" — multiple independent sources directly confirm the specific claimed detail - "partially_supported" — sources confirm the entity and domain; specific detail is pointed to but not directly stated - "insufficient_evidence" — sources don't address the specific claim; fires freely, including when the entity is well-known but the specific detail is undocumented - "unsupported" — a credible source explicitly contradicts the claim All verdicts are DECIDE-BY-EYE. A "supported" verdict means current web sources confirm it — not that it is true. Evidence may be incomplete, biased, or outdated. The stated_limits field is always present and identifies what the evidence cannot confirm. Good input shape (specific, checkable assertions): - "Werner Herzog dragged a full-size steamship over a hill during the filming of Fitzcarraldo" - "Glenn Gould stopped giving live concerts in 1964" - "The Backrooms photograph originated on 4chan" Checks one specific factual statement. Not for identifying half-remembered works. Not this shape: - "there's a documentary about a filmmaker dragging a boat over a mountain" - "a musician famous for stopping performing"

輸入參數claim必填

版本歷史

4
  1. v0.2.5最新Oct 12, 2026
  2. v0.2.4Oct 4, 2026
  3. v0.2.3Oct 1, 2026
  4. v0.2.2Sep 16, 2026

評分

已滿足適用檢查項的 100%

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