talkthrough-mcp

korovin-aa97/talkthrough-mcp

★ 4 stars Python AI/LLM Updated 2d ago

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.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "talkthrough-mcp": {
      "command": "uvx",
      "args": [
        "talkthrough-mcp"
      ]
    }
  }
}

Or install with pip: pip install talkthrough-mcp

README Excerpt

**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:

Tools (9)

TALKTHROUGH_HOMETALKTHROUGH_MAX_FRAMESTALKTHROUGH_MAX_SECONDSTALKTHROUGH_OCRTALKTHROUGH_OCR_LANGTALKTHROUGH_OCR_PARAMSTALKTHROUGH_WHISPER_MODELmediumsegments

Topics

agent-skillsai-agentsclaudedeveloper-toolsfeedbackffmpeglocal-firstmcpmcp-servermodel-context-protocolocrpythonscreen-recordingspeech-to-texttranscription

talkthrough-mcp

Quick Install

README Excerpt

Tools (9)

Topics

Related AI/LLM Servers