Skip to main content

Python rewrite for Plaud CLI and MCP workflows.

Project description

plaud-tools

Bridge your Plaud recordings into AI assistants via a Python CLI and an MCP server.

CI status: alpha Python License: LGPL-3.0-or-later

Alpha software. This project is pre-1.0. APIs, tool names, and CLI flags may change between minor versions. Pin a known-good version in production wiring and review the CHANGELOG before upgrading.

Unofficial — not affiliated with Plaud. The Plaud API is reverse-engineered from the Plaud web app. "Plaud" is a trademark of Plaud Inc.; this project is not affiliated with, endorsed by, or sponsored by Plaud. Use at your own risk: Plaud's Terms of Service may restrict reverse-engineering and automated access, and your account could be rate-limited or suspended. You still need a real Plaud account; this package does not replace the Plaud mobile or web apps.

Install

From PyPI:

pip install plaud-tools

Windows users can also grab a bundled tray app + frozen CLI + MCP server from the latest release (no Python install required). See docs/INSTALL.md for the full walkthrough.

Quickstart

# Sign in once. Region is `us` or `eu`; auto-detected on first API call.
plaud-tools login --email you@example.com --region us

# Recent recordings
plaud-tools list

# Full detail for one recording (title, date, duration, headline)
plaud-tools show <recording-id>

The CLI ships as both plaud-tools and the shorter alias pt. Run plaud-tools --help for the full subcommand list.

Wire the MCP server into your AI client

Log in via the CLI before starting the AI client; the MCP server reads the saved session automatically.

Claude Desktop — add to claude_desktop_config.json (Windows: %APPDATA%\Claude\claude_desktop_config.json; macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "plaud": {
      "command": "plaud-mcp"
    }
  }
}

Claude Code — same JSON block, in ~/.claude.json (user-level) or .claude.json at the project root.

Codex CLI — in ~/.codex/config.toml:

[mcp_servers.plaud]
command = "plaud-mcp"

Fully quit and relaunch the AI client after editing the config — MCP servers are loaded once at startup. Full wiring details, troubleshooting, and tray bundle install steps live in docs/INSTALL.md.

What's in the box

Entry point What it is
plaud-tools / pt Python CLI — list, search, transcribe, upload, rename, trash, merge recordings
plaud-mcp MCP server (stdio transport) — exposes the tool surface below to AI clients
plaud-tray (optional, pip install plaud-tools[tray]) Windows system-tray app for one-click sign-in and MCP wiring

MCP tool surface

The MCP server exposes 7 workflow-oriented tools (canonical list in src/plaud_tools/server.py):

Tool What it does
browse_recordings List and filter recordings by date, title, folder
get_recording Full detail for one recording; opt in to transcript / speakers / summary
mutate_recording Rename, trash, restore, delete, move to folder, rename speaker
upload_recording Upload a local audio file (transcodes via ffmpeg if needed)
process_recording Trigger transcription + summarization; block until both complete
list_folders List Plaud folders (id, name, color, icon)
merge_recordings Merge two or more recordings into a single new recording

Develop

git clone https://github.com/massive-value/plaud-tools.git
cd plaud-tools
pip install -e ".[dev]"
pytest -q

See CONTRIBUTING.md for the full contributor workflow, including the PLAUD_LIVE_READS=1 live-test gate.

Token & secrets

Plaud JWTs last ~300 days; plaud-tools auto-refreshes silently when the token is within 30 days of expiry. Sessions are stored in the OS keyring when available, with a mode-600 fallback at ~/.config/plaud-tools/session.json.

Docs

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

plaud_tools-0.1.8.tar.gz (63.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

plaud_tools-0.1.8-py3-none-any.whl (50.8 kB view details)

Uploaded Python 3

File details

Details for the file plaud_tools-0.1.8.tar.gz.

File metadata

  • Download URL: plaud_tools-0.1.8.tar.gz
  • Upload date:
  • Size: 63.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for plaud_tools-0.1.8.tar.gz
Algorithm Hash digest
SHA256 8be34b310126b9834084979b3830b629c0fc3786d01801801a2c7445313048d4
MD5 976ce163b258f038bd6d704fb93ea76b
BLAKE2b-256 1e493918771e42f4c81051fb7f7de244025880a5b3ada550cb0018eaef6e74d1

See more details on using hashes here.

Provenance

The following attestation bundles were made for plaud_tools-0.1.8.tar.gz:

Publisher: release.yml on massive-value/plaud-tools

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file plaud_tools-0.1.8-py3-none-any.whl.

File metadata

  • Download URL: plaud_tools-0.1.8-py3-none-any.whl
  • Upload date:
  • Size: 50.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for plaud_tools-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 b066627d77a6e79850710deada2d65081128b32d4677ba1cd203fb4f393deea4
MD5 0438fcdec1b96de04b227b8fa6e38042
BLAKE2b-256 35bfb1e967eae64946ce0a2223782707a00ce142e03211de2847033d0990a470

See more details on using hashes here.

Provenance

The following attestation bundles were made for plaud_tools-0.1.8-py3-none-any.whl:

Publisher: release.yml on massive-value/plaud-tools

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page