Speak-Y ships with a built-in Model Context Protocol server. Claude Code, Claude Desktop, Cursor, ChatGPT Desktop, Windsurf, VS Code, Zed, JetBrains AI Assistant, Raycast, Warp, Cline, Continue, Gemini CLI, LM Studio and any other MCP client can search your recordings and read transcripts, meeting summaries and action items — and, with the app running, tag a recording, name the speakers in a meeting or file it into a team channel.
Reading is local and needs nothing else running: search results and transcripts come straight off the library on your machine, with no cloud relay. Commands that change something — tags, titles, speaker names, re-transcription, sharing into a team channel — go through the running Speak-Y app. They are declared to your MCP client as data-changing, so it asks before running them unless you grant standing permission, and every one of them is logged in the app, where they can also be switched off.
Prefer an assistant that can only read? Start the server with --read-only in that client's config and the changing commands are not published at all — it sees search, transcripts, summaries, tags and the channel list, and nothing else.
One-click install from Settings → Integrations, and it is free on every plan, while meeting notetakers gate MCP behind paid cloud tiers.