Skip to main content

A Model Context Protocol (MCP) server that provides AI assistants with secure, read-only access to Google Keep notes and lists.

Project description

wlater MCP Server

Connect your AI assistant to Google Keep. Search, read, and manage your notes and lists through natural conversation.

Installation

pip install wlater-mcp

Setup

Run the setup wizard to configure your credentials:

wlater-setup

Choose your authentication method:

  • Automated: Opens Chrome and logs you in automatically
  • Manual: Enter your credentials directly

Configuration

Add to your MCP client's config file (e.g., claude_desktop_config.json):

{
  "mcpServers": {
    "wlater": {
      "command": "python",
      "args": ["-m", "wlater_mcp.server"]
    }
  }
}

Restart your AI assistant and you're ready!

Usage

Talk to your AI naturally:

  • "Show me all my pinned notes"
  • "What's on my shopping list?"
  • "Check off 'buy milk' from my grocery list"
  • "Create a note called 'Meeting Notes'"
  • "Add 'call dentist' to my todo list"
  • "Find notes labeled 'work'"

All changes are previewed before being saved to Google Keep.

Features

  • ✅ Read and search your Keep notes
  • ✅ Manage todo lists (check/uncheck items)
  • ✅ Create notes and lists
  • ✅ Add labels and change colors
  • ✅ Preview changes before syncing
  • ✅ Secure credential storage (OS keyring)
  • ❌ Cannot delete notes (safety feature)

Troubleshooting

"Master token not found"

wlater-setup

"Authentication failed"
Your token may have expired. Re-run setup.

Server not appearing
Check your config file paths and restart your MCP client.

Security

  • Credentials stored in your system keyring (Windows Credential Locker, macOS Keychain, Linux Secret Service)
  • Preview all changes before syncing
  • No automatic modifications
  • Delete operations not exposed

Links

License

MIT License - See LICENSE for details

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

wlater_mcp-0.1.0.tar.gz (22.7 kB view details)

Uploaded Source

Built Distribution

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

wlater_mcp-0.1.0-py3-none-any.whl (19.0 kB view details)

Uploaded Python 3

File details

Details for the file wlater_mcp-0.1.0.tar.gz.

File metadata

  • Download URL: wlater_mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 22.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for wlater_mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 9856863164076dd150f780fc4dd55136833da7aefd91ee0be163b2e62d3c9e4b
MD5 09226cf5a3d673f1f2579a618acbfbda
BLAKE2b-256 6ffc32c4c6eb173a0ea8f7eda5d0b02daf54c44bd653ff1f62823b0ddb2f4bb2

See more details on using hashes here.

File details

Details for the file wlater_mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: wlater_mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 19.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.7

File hashes

Hashes for wlater_mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f0ff6ec19ed456e08ca886a649ef620b608a8943e73ee45297d85683aa99cca0
MD5 4fbfe705cc3bdf8ef2ff7991c5ad5e14
BLAKE2b-256 a1ff34568a5f3a768403cea8690e2f18ee64056364d140445596d2ac28708e62

See more details on using hashes here.

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