Server Notify
Send system notification when Agent task is done.
What is Server Notify?
Server Notify is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to send system notification when agent task is done.
Send system notification when Agent task is done.
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Send system notification when Agent task is done.
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-server-notifyConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Server Notify
MCP Server Notify is a lightweight MCP server that sends desktop system notifications and plays an alert sound when an AI agent finishes a long-running task. It uses the Apprise API to deliver cross-platform notifications on Windows, macOS, and Linux, so you can step away from your desk while Claude works and be alerted the moment the task completes. It is especially useful for slow operations like code generation, batch processing, or multi-step research tasks.
Prerequisites
- Python 3.8+ and pip (or uv) installed
- Platform-specific notification support: pywin32 on Windows, terminal-notifier on macOS (brew install terminal-notifier), or a standard notification daemon on Linux
- An MCP-compatible client such as Claude Desktop or Cursor
Install platform notification dependencies
Install the OS-level notification support for your platform before installing the Python package.
# macOS
brew install terminal-notifier
# Windows (in your Python environment)
pip install pywin32Install the mcp-server-notify package
Install the package using pip or uv. The uvx approach is convenient for VS Code and Cursor.
pip install mcp-server-notify
# or with uv
uv pip install mcp-server-notifyVerify the installation
Confirm the server module can be loaded by running it directly.
python -m mcp_server_notifyAdd the server to your MCP client configuration
Edit your MCP client config to include the notification server. Use the python -m invocation for Claude Desktop or the uvx form for VS Code.
Instruct the agent to notify on task completion
When starting a long task, tell Claude to send a notification when it finishes. Add the instruction to your prompt.
Server Notify Examples
Client configuration
Claude Desktop configuration using the python -m invocation. For VS Code with Copilot, use uvx instead.
{
"mcpServers": {
"NotificationServer": {
"command": "python",
"args": ["-m", "mcp_server_notify"]
}
}
}Prompts to try
How to ask Claude to send you a notification after completing a task.
- "Refactor all the API endpoints in this project and send me a system notification when you're done"
- "Run the full test suite analysis and notify me when complete"
- "Generate documentation for every public function in this module, then send a desktop notification"
- "When you finish the task, send me a notification with a brief summary"Troubleshooting Server Notify
No notification appears on macOS
Ensure terminal-notifier is installed (brew install terminal-notifier) and that your terminal application has notification permissions in System Settings > Notifications.
No notification appears on Windows
Install the pywin32 package in the same Python environment used to run the server: pip install pywin32. Restart your Python environment after installation.
Server fails to start with import errors
Make sure you are running the correct Python interpreter that has mcp-server-notify installed. Use 'which python' or 'python --version' to confirm the right environment is active.
Frequently Asked Questions about Server Notify
What is Server Notify?
Server Notify is a Model Context Protocol (MCP) server that send system notification when agent task is done. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Server Notify?
Follow the installation instructions on the Server Notify GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Server Notify?
Server Notify works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Server Notify free to use?
Yes, Server Notify is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Server Notify Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Server Notify? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Server Notify in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Server Notify?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.