Message MCP
Supports sending email notifications through Gmail's SMTP server when AI tasks are completed
Provides native system notifications for Linux environments when AI tasks are complete
Delivers native system notifications for macOS when AI tasks are complete
Compatible with Ubuntu's default notification system for displaying alerts when AI tasks finish
Click on "Install 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., "@Message MCPnotify me when the data analysis is complete"
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.
🚀 Boost AI efficiency and free up more time
When waiting for AI to complete tasks, do you wish you could handle other work simultaneously? Now you can confidently take care of other matters while AI executes long-running tasks.
Message MCP makes your AI collaboration more efficient!
🧑: Make a Tetris web game, notify when completed.
🤖: I'll start making the Tetris game
...
💬: Message MCP executed, message sent.Allow MCP auto-execution in client settings.
Add "notify when completed" prompts in user rules or rule files to avoid repetitive manual prompts.
⚡️ Quick Installation
Supports cloud installation via smithery.ai (e.g., SaaS services like Dify) and offers one-click local deployment. Since the Message MCP actually runs on smithery.ai’s cloud, desktop notifications are not yet supported. End-to-end encryption is applied throughout to ensure data security. Learn more
⚙️ Standard Installation
MacOS, Linux, WSL2
{
"mcpServers": {
"message-mcp": {
"command": "npx",
"args": ["-y", "message-mcp@latest"]
}
}
}Windows
{
"mcpServers": {
"message-mcp": {
"command": "cmd",
"args": ["/c", "npx", "-y", "message-mcp@latest"]
}
}
}🎛️ Optional Configuration
Modify Desktop Notifications
{
"mcpServers": {
"message-mcp": {
"command": "npx",
"args": ["-y", "message-mcp@latest"],
"env": {
"DISABLE_DESKTOP": "true",
"SOUND_PATH": "/path/to/your/sound.mp3"
}
}
}
}
Desktop notifications are enabled by default
Default sound provided by zapsplat. If you don't like the default sound, you can download and configure from zapsplat.com.
ntfy Mobile Notifications
Install App: App Store, Google Play, F-Droid
{
"mcpServers": {
"message-mcp": {
"command": "npx",
"args": ["-y", "message-mcp@latest"],
"env": {
"NTFY_TOPIC": "your-unique-topic"
}
}
}
}Email Notifications
{
"mcpServers": {
"message-mcp": {
"command": "npx",
"args": ["-y", "message-mcp@latest"],
"env": {
"SMTP_HOST": "smtp.gmail.com",
"SMTP_PORT": "587",
"SMTP_SECURE": "false",
"SMTP_USER": "user@gmail.com",
"SMTP_PASS": "your_password"
}
}
}
}API Notifications
{
"mcpServers": {
"message-mcp": {
"command": "npx",
"args": ["-y", "message-mcp@latest"],
"env": {
"API_URL": "https://httpbin.org/post",
"API_METHOD": "POST", // POST, PUT, PATCH
"API_HEADERS": "{\"Authorization\": \"Bearer token\"}"
}
}
}
}fetch(API_URL, {
method: API_METHOD,
headers: {
'Content-Type': 'application/json'
...JSON.parse(API_HEADERS)
},
body: JSON.stringify({
title: notifyTitle,
message: notifyMessage,
}),
})Related MCP server: Notification AI MCP
📌 System Requirements
Node.js: 18 or higher
macOS: Native notifications require >= 10.8
Linux: notify-osd or libnotify-bin installed (Ubuntu includes by default)
Windows: >= 8, or taskbar balloon notifications for Windows < 8
❗️ Troubleshooting
Windows System Notifications Not Enabled
Settings > Notifications & actions > Get notifications from apps and other senders → Enable
WSL2 (Ubuntu) has no notification sound
sudo apt install -y pulseaudio mpg123WSL2 Environment Missing OS Notifications
sudo find / -type f -name "snoretoast-*.exe" 2>/dev/null
/path/to/.../node_modules/snoretoast-x64.exe
/path/to/.../node_modules/snoretoast-x86.exe
chmod +x /path/to/.../node_modules/snoretoast-*.exeIf this project is helpful to you, please give it a ⭐️ to support it and let more people see it!
Available Tools
1 toolnotifySend Message NotificationA
Send notifications and messages through multiple channels (desktop, email, API). Use this tool to notify users about any important information, progress updates, task completions, alerts, or any other communication needs.
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | The title of the notification | |
| message | No | The main content of the notification message |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It claims multi-channel delivery but does not clarify if all channels are always used or if there is implicit selection. No mention of side effects, permissions, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words. First sentence states purpose and channels, second gives use cases. Very concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with no output schema and two string parameters, the description covers purpose and use cases adequately. However, it lacks clarity on channel selection and does not specify the return type (likely void).
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description does not add meaning beyond the schema for the parameters; it only states the notification's purpose.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'send' and resource 'notifications/messages', and specifies multiple channels (desktop, email, API). Though there are no sibling tools, the purpose is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Use this tool to notify users...' and lists use cases, but it does not provide when not to use or mention that channel selection is not available via parameters, which could mislead an agent.
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. Dates show when Glama detected each change.
1 tool update
- First observed
notify
TDQS
Only one tool exists, so no possibility of confusion or overlap.
Single tool uses a clear, verb-based name 'notify' which is consistent with its purpose.
One tool for a notification domain is too few; typically multiple operations (e.g., send, schedule, manage templates) are needed.
The tool sends notifications but lacks capabilities for managing channels, templates, logs, or preferences, leaving significant gaps.
Maintenance
Related MCP Connectors
- call-meOAuthapp.getcallme
Calls your phone when an AI task finishes or is blocked — hear it, say what's next.
Let your AI agent notify you by email, Slack, Discord, or webhook. One tool: send_notification.
Push notifications for AI agents - send instant iPhone notifications from any MCP client.
Build and send email, SMS, and push straight from your AI agent.
Related MCP Servers
- AlicenseBqualityFmaintenanceA Model Context Protocol service that sends desktop notifications and alert sounds when AI agent tasks are completed, integrating with various LLM clients like Claude Desktop and Cursor.154MIT
- AlicenseNot gradedqualityBmaintenanceNotification AI - MCP server providing AI-powered tools and automation by MEOK AI Labs15MIT
- AlicenseNot gradedqualityCmaintenanceEnables sending real-time and webhook notifications when AI agents complete tasks, with support for Discord, Slack, Teams, Feishu, Ntfy, and custom webhooks.6MIT
- AlicenseBqualityDmaintenanceEnables AI development tools on Windows to send native system notifications for task completion, errors, and reminders, with customizable icons and sounds.7177MIT
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gimjin/message-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server