Talkthrough MCP Server

Narrated screen recordings into agent-ready data: local transcript, keyframes, OCR, wall-clock.

Local serverstdioGo

What is the Talkthrough MCP server?

Talkthrough MCP server exists for a simple reason — assistants are far more useful when they can act on Talkthrough directly instead of describing what you should do. Narrated screen recordings into agent-ready data: local transcript, keyframes, OCR, wall-clock.

What you get

Give Claude Code or Codex a narrated .mov/.mp4 — talkthrough turns it into searchable transcript, exact frames, OCR and wall-clock timestamps, locally — so your agent writes an evidence-backed issue draft or investigates the fix.

Setting it up

The server ships on PyPI as args, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once Talkthrough is connected, these are the calls the assistant has available:

  • Prompt — Workflow
  • bug — One recording → evidence-backed GitHub issue draft (silent, narration-free recordings work too)
  • triage-recording — Narrated screencast → precise findings JSON (bug/feature/question routing, frame evidence)
  • spec-from-workshop — Recorded workshop → structured spec with quoted decisions and open questions
  • backlog-from-demo — Product demo → prioritized backlog with timestamped evidence
  • meeting-actions — Meeting audio → action items, decisions, open questions
  • correlate-with-logs — Recording remarks ↔ system logs via wall-clock windows

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the talkthrough mcp server does with a few real requests.

Choosing this one

This sits in the monitoring and observability group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Talkthrough's toolset — Prompt, bug, triage-recording and 4 more — is a fair guide to whether it matches your workflow. It is maintained by korovin-aa97; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Talkthrough's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
PromptWorkflow
bugOne recording → evidence-backed GitHub issue draft (silent, narration-free recordings work too)
triage-recordingNarrated screencast → precise findings JSON (bug/feature/question routing, frame evidence)
spec-from-workshopRecorded workshop → structured spec with quoted decisions and open questions
backlog-from-demoProduct demo → prioritized backlog with timestamped evidence
meeting-actionsMeeting audio → action items, decisions, open questions
correlate-with-logsRecording remarks ↔ system logs via wall-clock windows

How to install the Talkthrough MCP server

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

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Talkthrough to Prompt.
  • Use Talkthrough to bug.
  • Use Talkthrough to triage-recording.

Frequently asked questions

It connects Talkthrough to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (Prompt, bug, triage-recording, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Talkthrough directly.