Video Reader MCP

io.github.SylphxAI由 GitHub 账号 SylphxAI 发布v0.1.0更新于 Oct 24, 2026

Evidence-first video MCP. Timeline document with ffprobe streams and subtitle cues.

已验证STDIO仅桌面文件与存储媒体与设计

概览

AI 生成的概览

本地 MCP 服务器,为助手提供可搜索、带时间戳的本地视频时间线,并按需生成画面证据。

可以做什么
  • 读取本地视频的容器元数据、流、章节和内嵌字幕,quality 配置下可额外启用 ffmpeg 场景检测
  • 在内嵌字幕中搜索引文并返回带时间戳的匹配
  • 在已知时间戳处渲染、裁剪或 OCR 单帧作为后续证据
  • 将缺少 ffprobe 或字幕的情况明确报告为缺口,而不是猜测
适用场景
适合需要就本地视频文件回答问题的场景,例如查找某句台词、按章节总结会议、定位演示中的某个时刻,并要求每个结论都能引用时间戳、流索引或源哈希。不适合没有内嵌字幕的视频,也不做语音转写。
运行要求
以本地 stdio 进程运行,通常通过 npm 包用 npx 启动;元数据读取需要 ffprobe,引文搜索需要视频自带内嵌字幕。未声明任何认证、环境变量或请求头。仓库已归档,README 称项目已合并到另一个包。
安装前请注意
README 说明仓库已归档并指向后继包,安装前应确认维护状态。它不做语音识别、关键帧或转写:开启 include_keyframes 或 include_transcript 只会返回警告和空数组。帧渲染与 OCR 在本地对你指定的文件执行。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Video Reader MCP,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

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

来源:README.md,提交 30773b7

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.1.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分