talkthrough-mcp is an open-source, local-first MCP server that processes narrated screen recordings to produce structured data, including timestamped transcripts, scene keyframes, OCR text, and wall-clock anchoring. It is designed for AI developers and automation engineers who need to convert video and audio content into agent-ready formats.
talkthrough-mcp sits in PulseGate's Other AI category. It focuses on extracting structured, agent-ready data from narrated screen recordings for automation and analysis. It is built as an open-source project for AI developers and automation engineers. talkthrough-mcp is open source under the MIT license. It ships for the command line, and it can be self-hosted.
Behind talkthrough-mcp is korovin-aa97, and it first shipped in 2026. The project is developed in the open on GitHub with 19 commits in the last 90 days. Among its 5 catalogued features are screen recording ingestion, timestamped transcription, and scene keyframes extraction. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do