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.
Quickstart · Tools · FAQ · Troubleshooting · Changelog · Contributing
Feedback ingestion for AI agents. Record your screen and talk; your agent does the rest — files the bugs, writes the spec, builds the backlog.
talkthrough-mcp is a local-first MCP server that turns a narrated screen recording (or any video/audio file) into agent-ready structured data: timestamped transcript segments, scene-change keyframes, OCR'd on-screen text, and wall-clock anchoring. Everything is served through lazy retrieval tools, so a 30-minute recording never floods the model context — the agent pulls exactly the transcript slice, moment bundle, or frame it needs.
There is no LLM inside the server and no cloud anywhere in the path: ffmpeg, faster-whisper, and RapidOCR run on your machine, and the calling agent brings the intelligence. What makes it different from screen-recorder SaaS and video-analyzer MCPs: it works on arbitrary local files, it ships the agent workflows (server prompts + example agents), and it anchors every timestamp to wall-clock time — so "the moment I said the checkout hung" maps straight to the right window of your server logs.
One command, no system dependencies: ffmpeg falls back to a bundled build, OCR is pip-only, and whisper models download themselves on first use.
Two install paths — pick one, not both (the plugin already includes the server; installing both would register it twice):
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/korovin-aa97--talkthrough-mcp.html)
Annotated screenshots for AI agents: Skitch-style arrows, numbered steps, boxes, labels, solid redaction
NitcanKen/Codex-native-long-video-memoryLocal-first Codex plugin that indexes long videos with OCR/ASR and answers with timestamped, SHA-verified visual evidence.
00200200/usagetrimKeep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
alphaparkinc/genpark-role-playing-autonomous-agent-crew-orchestrator-skillRole-playing autonomous agent orchestrator managing crews (CrewAI style)
alphaparkinc/genpark-realtime-neural-3d-mesh-pbr-texture-generator-skillReal-time neural 3D asset generator and PBR texture synthesizer (Luma Genie style)
alphaparkinc/genpark-multivariate-ad-creative-fatigue-auditor-skillMultivariate ad creative fatigue auditor & refresh triggers (AdEspresso style)
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.