A
licenseB
qualityD
maintenanceEnables 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.
1
9
MIT
mcp-win-toast
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-win-toastSend a toast alert if disk space drops below 10GB"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-win-toast
An MCP (Model Context Protocol) server that lets AI assistants send Windows toast notifications and dialog boxes. Give your AI a voice on your desktop.
Why mcp-win-toast?
AI assistants are powerful — but they work silently in the background. With mcp-win-toast, your AI can actively notify you through native Windows UI, turning it into a true desktop companion.
Related MCP server: Notifications MCP Server
Use Cases
Long Task Completion Alert
Ask the AI to analyze a large codebase, generate a report, or run a complex workflow — and get a toast notification the moment it's done. No need to keep watching the screen.
"Refactor all the API endpoints, and notify me when you're finished."
Scheduled Reminders
Combine with other MCP tools to set up reminders that pop up as native Windows notifications.
"Remind me in 30 minutes to check the deployment status."
Build & Test Result Notifications
Let the AI run your build pipeline or test suite and push the result as a toast — pass or fail, you'll know right away.
"Run the tests and show me a toast with the results."
Important Decision Checkpoints
Use dialog boxes to force a pause and get explicit user confirmation before the AI proceeds with a critical action.
"Before deleting any files, show me a dialog to confirm."
System Monitoring Alerts
Have the AI periodically check disk space, CPU usage, or service health, and alert you only when something needs attention.
"Monitor my disk space and warn me if it drops below 10GB."
Tools
show_toast
Displays a Windows toast notification.
Parameter | Type | Description |
title | string | Notification title |
message | string | Notification body text |
show_dialog
Displays a standard Windows dialog box with an OK button. Execution is blocked until the user clicks OK, making it ideal for confirmations and important alerts.
Parameter | Type | Description |
title | string | Dialog title |
message | string | Dialog body text |
Setup
git clone https://github.com/ShigeruWakida/mcp-win-toast.git
cd mcp-win-toast
npm install
npm run buildClaude Desktop Configuration
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"win-toast": {
"command": "node",
"args": ["C:\\path\\to\\mcp-win-toast\\build\\index.js"]
}
}
}Combo: mcp-win-toast + YakusokuKeeper
YakusokuKeeper is an MCP server that enforces rules on Claude's behavior based on time, input count, or first interaction. By combining it with mcp-win-toast, you can build a self-managing AI assistant that notifies you at the right moments — automatically, without being asked.
Break Reminder
Add a time-based rule in YakusokuKeeper to remind you to take a break every 30 minutes, delivered as a toast notification.
YakusokuKeeper rule:
time_based:
- rule: "Call show_toast with title 'Break Time' and message 'You have been working for 30 minutes. Stand up and stretch!'"
minutes: 30Progress Report at Regular Intervals
Have Claude automatically summarize what it has done every 10 interactions and notify you.
YakusokuKeeper rule:
input_count:
- rule: "Summarize what you have accomplished so far in 2-3 bullet points, then call show_toast with title 'Progress Report' and the summary as the message."
count: 10Welcome Briefing on Session Start
Greet the user with a toast notification and a quick status overview at the beginning of every session.
YakusokuKeeper rule:
first_time:
- rule: "Call show_toast with title 'Session Started' and message 'Hello! Ready to assist you. Let me know what you need.' as a greeting."Critical File Protection
Show a blocking dialog for confirmation whenever Claude is about to modify important files.
YakusokuKeeper rule:
first_time:
- rule: "Before editing any file matching *.env, *.config, or docker-compose.*, always call show_dialog with title 'Confirm Edit' and a message describing which file you are about to modify. Wait for the user to acknowledge before proceeding."Session Duration Warning
Warn the user with a dialog box after a long session so they can decide whether to continue.
YakusokuKeeper rule:
time_based:
- rule: "Call show_dialog with title 'Long Session' and message 'You have been working for over an hour. Would you like to wrap up or continue?' to check in with the user."
minutes: 60Prompt Examples for Claude Code
You can also give these instructions directly as prompts in Claude Code:
Every time you finish a task, send me a toast notification with a brief summary.If you are about to delete or overwrite any file, show a dialog box to confirm before proceeding.After every 5 messages, show a toast with a short progress update of what we have accomplished.Requirements
Windows 10 / 11
Node.js 18+
License
ISC
Available Tools
2 toolsshow_dialogC
Windows標準のOKボタン付きダイアログボックスを表示します
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | ダイアログのタイトル | |
| message | Yes | ダイアログのメッセージ本文 |
TDQS
C2.9/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description should disclose behavioral traits. It only states that a dialog is displayed with an OK button, but omits details like whether the dialog is modal, whether it blocks execution, or what happens after the button is clicked.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence in Japanese that efficiently conveys the tool's purpose. It is appropriately concise, though a bit more structure could improve readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (2 required parameters, no output schema), the description is minimally complete. It tells what the tool does, but does not explain return values or interaction behavior. For a dialog tool, this is acceptable but not exemplary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of parameters with descriptions for both 'title' and 'message'. The description adds no additional meaning beyond what the schema already provides, so the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool displays a Windows standard dialog box with an OK button. It specifies the verb (display) and resource (dialog box). However, it does not explicitly differentiate from the sibling tool 'show_toast', though the context implies a difference.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus the alternative 'show_toast'. There is no mention of suitable scenarios, prerequisites, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
show_toastB
Windowsのトースト通知を表示します
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | 通知のタイトル | |
| message | Yes | 通知のメッセージ本文 |
TDQS
B3.3/5.0
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose any behavioral traits beyond the basic action. It lacks information on potential side effects, permissions, or whether multiple toasts stack.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that immediately communicates the tool's purpose. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with two required string parameters and no output schema, the description is minimally sufficient but lacks guidance on edge cases, behavior expectations, or integration context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with Japanese descriptions for both 'title' and 'message'. The description does not add additional meaning beyond what the schema already provides, so a baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Displays a Windows toast notification' is a specific verb+resource combination that clearly states what the tool does. It distinguishes from sibling 'show_dialog' which likely shows a dialog, not a toast.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus the sibling 'show_dialog' or other alternatives. There is no mention of context, prerequisites, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v1.0.0- First observed
show_dialog - First observed
show_toast
TDQS
B3.4/5.0
Scored across 2 tools
Disambiguation5/5
The two tools serve clearly distinct purposes: show_dialog displays a modal dialog box with an OK button, while show_toast shows a non-modal toast notification. An agent can easily differentiate them based on the behavior.
Naming Consistency5/5
Both tool names follow the consistent verb_noun pattern (show_dialog, show_toast), making the naming predictable and easy to understand.
Tool Count4/5
With only 2 tools, the server is minimal, but for its specific domain of Windows notification types, the count is reasonable and not excessive. It could benefit from additional dialog variations, but the current scope is justifiable.
Completeness4/5
The server covers the two most common Windows notification types (dialog and toast). Minor gaps exist, such as the lack of dialogs with custom buttons or toast with actions, but the core functionality is present.
Maintenance
ActivityInactive
ResponsivenessNo issues
Related MCP Connectors
Push notifications for AI agents - send instant iPhone notifications from any MCP client.
Reach your own phone from an AI agent: notifications, approval questions, reminders, ring, files.
Let your AI agent notify you by email, Slack, Discord, or webhook. One tool: send_notification.
Let your AI sessions talk to each other — messaging, tasks, sessions, and alerts
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to send native macOS notifications for task completion alerts and reminders. Supports interactive features like custom system sounds, action buttons, and user replies directly from the notification center.201MIT
- AlicenseBqualityDmaintenanceEnables AI assistants to send desktop notifications on macOS with rich formatting, urgency levels, and sound options.1111MIT
- AlicenseBqualityDmaintenanceEnables AI development tools on Windows to send native system notifications for task completion, errors, and reminders, with customizable icons and sounds.7107MIT