Cue

io.github.SylphxAI由 GitHub 帳號 SylphxAI 發布v0.3.5更新於 Oct 24, 2026

Cue — video answers with timestamp-level proof. Scenes and frames stay off until asked.

已驗證STDIO僅桌面檔案與儲存媒體與設計

概覽

AI 產生的概覽

Cue 是一個本機 MCP 伺服器,為助理提供可搜尋的本機影片時間軸,回傳章節、內嵌字幕與帶時間戳記的位置。

可以做什麼
讀取本機影片檔案,取得容器中繼資料、串流、章節與內嵌字幕,可透過 quality 設定或場景開關啟用場景偵測。在內嵌字幕中搜尋台詞,回傳帶時間戳記的相符結果。在已知時間戳記處算圖、裁切或 OCR 單一影格,作為後續證據。對缺少 ffprobe 或沒有字幕等情況回報為缺口,而不是猜測。將每筆結果連結到時間戳記、串流索引、字幕範圍或來源雜湊。
適用情境
當助理需要回答關於本機影片檔案的問題時適用,例如哪一章講了某個主題、某句台詞出現在哪裡、某個時間點的畫面是什麼,並且應引用時間戳記而不是編造轉錄文字。
執行需求
以本機 stdio 程序執行,透過 npx 從 npm 套件 @sylphx/cue 啟動。需要以絕對路徑提供本機影片檔案,並需要 ffprobe 讀取中繼資料;未宣告雲端影片 API、帳號、API 金鑰或環境變數。
安裝前請注意
儲存庫已封存,專案已合併到另一個工具,可能不再維護。不執行語音辨識,台詞搜尋只比對內嵌字幕,結果可能為空。場景、影格與轉錄選項有限:關鍵影格與轉錄會回傳警告和空陣列,OCR 僅透過證據工具執行。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Cue,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。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

Merged into anymd (2026-09-25). anymd reads PDFs, Office files, EPUB, web pages, images and video into clean Markdown for AI agents: npx -y @sylphx/anymd. This repository is archived.

Cue

Video answers with timestamp-level proof

Cue gives agents a local video timeline they can search and cite. The default read returns container metadata, streams, chapters, and embedded subtitles. Scenes and frames are separate.

bash
npx -y @sylphx/cue

For Claude Code:

bash
claude mcp add cue -- npx -y @sylphx/cue

Read a local video

json
{  "sources": [{ "path": "/absolute/path/to/demo.mp4" }]}

That call uses the fast profile. It returns container metadata, streams, chapters, and embedded subtitles. It does not detect scenes, extract frames, or run speech recognition.

Then ask:

“Which chapter covers the pricing change?”

Cue returns chapter and subtitle locators with timestamp_ms and the source hash. It does not invent a transcript. A quote search matches embedded subtitles only. Render or crop a frame afterwards with video_evidence, once you have a timestamp.

Jobs Cue is built for

Ask your agentCue returns
“Find this quote.”a timestamped match in embedded subtitles, when those subtitles exist
“Summarize this meeting.”chapters and embedded subtitles
“Where is the code shown?”one frame from video_evidence at a known timestamp
“What changed in this demo?”scene boundaries when profile is quality or include_scenes is set
“Give me the useful moments.”chapters, embedded subtitles, warnings, and gaps

Tool surface

ToolPurpose
read_videoDefault fast profile: container metadata, streams, chapters, and embedded subtitles. Scenes are opt-in.
search_videoSearch embedded subtitle cues. It does not run speech recognition.
video_evidenceNamed follow-up: render, crop, or OCR one frame at a timestamp

Predictable defaults

  • Omitted profile is fast: container metadata, streams, chapters, and embedded subtitles. No scenes, frames, or speech recognition.
  • profile quality adds ffmpeg scene detection. It does not extract frames or run speech recognition.
  • include_keyframes and include_transcript stay off. Setting either one on the shipped server returns a warning and an empty array.
  • OCR stays on video_evidence.
  • No cloud video API or frame-by-frame vision model is required.
  • Missing ffprobe or embedded subtitles is reported as a gap, not guessed around.

Why agents trust it

Every claim can point back to timestamp_ms, a stream index, a subtitle range, or the source hash. A frame index is present only after video_evidence.

Companion MCP tools

ProductJob
CitraPDF answers with page-level proof
IrisImage facts and pixel evidence
SpineRepository architecture and impact
LocusExact code-chunk retrieval
LookoutWeb research with source excerpts

Each product is independent. Install only the tools your agent needs.

Development

bash
bun installbun run buildbun testcargo testbun run benchmark:public-proofbun run benchmark:release-gate

License

MIT

來源:README.md,提交 30773b7

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

4
  1. v0.3.5最新Sep 23, 2026
  2. v0.3.4Sep 23, 2026
  3. v0.3.3Sep 23, 2026
  4. v0.3.2Sep 23, 2026

評分

已滿足適用檢查項的 50%

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25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分