wlater Server
Unofficial MCP server for Google Keep - AI-powered access to your todos, lists, and notes
claude mcp add --transport stdio briansbrian-wlater-mcpserver python -m wlater_mcp.server
How to use
wlater MCP Server connects your AI assistant to Google Keep, enabling natural-language interactions to search, read, and manage notes and lists. With wl ater, you can query for pinned notes, shopping lists, labeled notes, and notes with images, and you can create or update notes, to-dos, and lists through conversational prompts. The server exposes the wl ater_mcp.server module as the MCP endpoint so your client can send natural-language requests and receive structured Keep data in response. Typical interactions include asking to show all pinned notes, display items on a shopping list, or create a new note with a given title.
To use it, configure your MCP client to point at this server using the Python-based entry point specified in the configuration (python -m wl ater_mcp.server). After starting your MCP client, you can converse with your assistant to manage Keep data. All changes are typically previewed before being saved, and you can filter by labels, colors, pins, and archived status, as described in the usage section of the project documentation.
How to install
Prerequisites:
- Python 3.8+ (or compatible Python environment)
- pip (Python package manager)
Installation steps:
-
Install the wl ater MCP package: pip install wlater-mcp
-
Optional: If you plan to use automated Google authentication via Selenium, install Selenium: pip install selenium
-
Run the setup (automatic authentication): wlater-setup token This will open a browser window for you to log in and extract the token.
-
If automated setup fails or you prefer manual setup, run: wlater-setup You will need your master token and follow the prompts. Refer to linked authentication documentation in the repository for gpsoauth and gkeepapi if needed.
Configuration:
- In your MCP client config, reference the server entry as shown in the README (Python module entry point).
Additional notes
Notes and tips:
- This MCP server uses Google Keep via gkeepapi and stores credentials securely in your system keyring.
- Ensure you have network access to Google Keep and that authentication tokens are refreshed as needed.
- The provided configuration supports both VS Code MCP.json format and generic MCP client JSON formats.
- If you encounter authentication issues, re-run wlater-setup (token) to re-authenticate.
- No automatic modifications are performed; changes are previewed before saving to Google Keep.
- If automated setup does not work, verify Selenium and WebDriver installation as described in the troubleshooting notes of the project.
Related MCP Servers
nautex
MCP server for guiding Coding Agents via end-to-end requirements to implementation plan pipeline
mcp-yfinance
Real-time stock API with Python, MCP server example, yfinance stock analysis dashboard
pfsense
pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI compliance check" instead of navigating complex interfaces. Supports REST/XML-RPC/SSH connections, and includes built-in complian
cloudwatch-logs
MCP server from serkanh/cloudwatch-logs-mcp
servicenow-api
ServiceNow MCP Server and API Wrapper
the -company
TheMCPCompany: Creating General-purpose Agents with Task-specific Tools