MCP.so
登录

Talkthrough

@korovin-aa97

关于 Talkthrough

MCP server: turn narrated screen recordings into agent-ready data — local Whisper transcript, scene keyframes, OCR, wall-clock anchoring. Record your screen, talk — your AI agent files the bugs.

配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块,请前往代码仓库查看安装说明。

代码仓库

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

talkthrough-mcp is a local-first MCP server that turns a narrated screen recording (or any video/audio file) into structured data for AI agents: timestamped transcript, scene keyframes, OCR of on-screen text, and wall-clock anchoring so spoken remarks map to real timestamps (e.g., to correlate with server logs). No cloud, no LLM inside — everything runs on your machine. One-command install: uvx talkthrough-mcp. MIT.

评论

AI 与智能体 分类下的更多 MCP 服务器