Enables AI assistants to send push notifications through the kweenkl iOS app using webhook tokens, with support for different priority levels and custom metadata
kweenkl MCP Server
🚀 PRE-LAUNCH: kweenkl is currently in pre-launch mode. Join our early access program to get notifications from your AI assistant!
MCP (Model Context Protocol) server that allows AI assistants to send kweenkl notifications.
What is kweenkl?
The verb "kweenkl" means to send a notification using kweenkl. When an AI can "kweenkl" you, it transforms from a conversational tool into an active assistant that can tap you on the shoulder when needed.
Pre-Launch Access
kweenkl is currently in pre-launch. During this phase:
The service is fully functional and ready to use
We're gathering feedback from early adopters
Official launch coming soon with more features
Try it now with our demo webhook token: 51fa2b2d-2080-4a73-b059-7e67712d93f7
Installation
Configuration
Claude Desktop (macOS)
Edit: ~/Library/Application Support/Claude/claude_desktop_config.json
Claude Desktop (Windows)
Edit: %APPDATA%\Claude\claude_desktop_config.json
Other MCP Clients
Consult your MCP client's documentation for stdio server configuration. The server requires:
Node.js executable
Path to index.js
Optional environment variables
Usage
Once configured, ask your AI assistant:
"kweenkl me when you're done"
"Send a high priority kweenkl about the deployment"
"kweenkl the team with the summary"
Example Interactions
Basic notification:
With priority:
Contextual notification:
Getting Your Webhook Token
Option 1: Use Demo Token (Pre-Launch)
Try kweenkl immediately with our demo webhook token:
This demo token lets you test the service right away. Notifications sent to this token will be delivered to the kweenkl team's test channel.
Option 2: Get Your Own Token
Open kweenkl iOS app (join our TestFlight for pre-launch access)
Open a channel
Tap info icon
Copy webhook token
Environment Variables
KWEENKL_API_URL
- API base URL (default: https://api.kweenkl.com)KWEENKL_DEBUG
- Enable debug logging (set to 'true')
Tool Parameters
The kweenkl
tool accepts the following parameters:
webhook_token
(required): Your channel's webhook tokenmessage
(required): The notification message (max 500 chars recommended)title
(optional): Brief title for the notification (max 50 chars recommended)priority
(optional): Priority level - "low", "normal" (default), or "high"payload
(optional): Custom JSON object for additional metadata
Testing
Run the test suite:
Or test manually with the MCP Inspector:
Troubleshooting
Issue | Solution |
Server not appearing in AI | Check JSON syntax in config file, verify file path, restart AI client |
404 errors | Verify webhook token in kweenkl app |
No notifications received | Ensure you're subscribed to the channel in the iOS app |
Network errors | Check firewall/proxy settings, ensure api.kweenkl.com is accessible |
Requirements
Node.js 18+
Valid kweenkl webhook token
Internet connection
License
MIT
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Tools
Enables AI assistants to send push notifications through the kweenkl service. Allows users to receive contextual notifications from their AI when tasks are complete or important events occur.