Plaud MCP Server

Plaud

Plaud Note and Plaud NotePin are hardware AI voice recorders. Recordings sync from the device to the user's Plaud cloud account. The cloud runs the audio through speech-to-text, plus an LLM, to produce a transcript, an automatic summary, and a list of action items. The user can also write a free-form note alongside the AI summary.

This bundle is a read-only view of one Plaud account. It cannot upload, delete, transcribe, or modify recordings. It cannot create or edit notes, summaries, or device entries. The web app at web.plaud.ai and the iOS / Android Plaud apps remain the place to do all of that.

How a Plaud account is shaped

• User — one account, identified by email. Has a region (the AWS region the account was created in), a membership tier (free / Pro / Unlimited), monthly transcription quota, and a Stripe subscription if paid.
• Devices — Plaud Notes and NotePins paired to the account. Each carries a serial number, model, firmware version, and battery state.
• Recordings (file) — every captured audio clip. Carries: filename, duration in seconds, capture date, file size, MD5, source device serial, "scene" tag (meeting / interview / lecture / …), and an in-row trans_result array of {start_ms, end_ms, content} segments produced by the on-device or cloud transcriber.
• AI artifacts (per recording) — every AI-generated derivative of the audio is an artifact under that recording's detail response. The two confirmed artifact families are:
  • auto_sum_note — the auto-generated markdown summary. Inlined as text in pre_download_content_list[].data_content.
  • consumer_note — the user's hand-edited markdown note for that recording (free-form, optional). Inlined the same way.
  • source_transaction — a binary blob that backs the raw transcript pipeline. Useful as a pointer; the human-readable transcript is the inline trans_result segments on the recording itself.

pre_download_content_list[] is the artifact list with content already in the response (data_content is the actual markdown). content_list[] is the parallel list with just metadata + a pre-signed S3 link (data_link — fetchable without an Authorization header). When a tool returns artifacts, prefer the pre_download_content_list content if it's there because it saves a second round-trip.

Each artifact id has the shape {type}:{short_hash}:{file_id} so an artifact's family can be read off the prefix without joining to anything.

Tools, in workflow order

1. plaud_get_user_profile — confirm the connected account (email, plan, transcription quota, region). Run this first to confirm the token works.
2. plaud_list_devices — see which Plaud Notes / NotePins are paired to this account.
3. plaud_read_recordings — without file_id, list every recording on the account (each row includes the inline trans_result segments, so for many use-cases this single call is enough). With file_id, return that recording's full detail, including the AI artifact lists.
4. plaud_get_transcript — the transcript view of one recording: every {start_ms, end_ms, content} segment from trans_result.
5. plaud_get_summary — the auto-generated markdown summary for one recording (the auto_sum_note artifact).
6. plaud_get_user_notes — the user's hand-edited markdown note for one recording (the consumer_note artifact). Empty when the user hasn't written one.
7. plaud_get_audio_download_url — a downloadable URL to the original audio. Plaud requires the same Bearer token on the audio download URL, so the response includes the full URL plus the exact Authorization header to send.
8. plaud_get_ai_task_status — poll the AI processing pipeline for a list of recording ids. Useful when a recording was just uploaded and the transcript / summary haven't appeared yet.

Region routing is automatic

Plaud runs separate regional API servers (api-euc1, api-use1, api-apse1, …) and the JWT carries which region the user belongs to. Tools always go to the correct regional host. There is nothing to configure.

What this bundle does not do

• It does not upload audio. The hardware device + the official Plaud apps own that path.
• It does not delete recordings. Use the Plaud app.
• It does not regenerate summaries with a different prompt or template. Use the Plaud app.
• It does not see other people's recordings. The bearer token is scoped to one Plaud account.