MCP Notify
A 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.
What is MCP Notify?
MCP Notify is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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.
A 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.
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol service that sends desktop notifica
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-notify-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Notify
MCP Notify Server is a lightweight MCP service that sends desktop notifications with an alert sound when an AI agent finishes a task, solving the problem of not knowing when a long-running Claude or Cursor job is done. It integrates with any MCP-compatible client — Claude Desktop, Cursor, VS Code with Copilot — and uses the cross-platform Apprise notification library to deliver native system notifications on Windows, macOS, and Linux. Developers add a single instruction to their prompt ("send me a notification when done") and the server handles the rest.
Prerequisites
- Python 3.10 or higher
- uv package manager or pip
- An MCP-compatible client: Claude Desktop, Cursor, or VS Code with Copilot in agent mode
- macOS: terminal-notifier installed via Homebrew ('brew install terminal-notifier')
- Windows: pywin32 installed ('pip install pywin32')
Clone the repository
Clone the mcp_server_notify repository to your machine.
git clone https://github.com/Cactusinhand/mcp_server_notify.git
cd mcp_server_notifyCreate a virtual environment
Set up an isolated Python environment for the server.
uv venv
source .venv/bin/activate # Windows: .venv\Scripts\activateInstall the package
Install mcp-server-notify and its dependencies. The package is also available on PyPI.
uv pip install mcp-server-notify
# or:
pip install mcp-server-notifyInstall platform-specific notification dependency
The server uses Apprise for cross-platform notifications, which needs a native helper per OS. Install the one for your operating system.
# macOS:
brew install terminal-notifier
# Windows:
pip install pywin32Verify the server runs
Run the module directly to confirm installation is successful. Use --debug to see verbose output.
python -m mcp_server_notify
# or with debug logging:
python -m mcp_server_notify --debugConfigure your MCP client
Add the server to your client's configuration file. The path in --directory must be the absolute path to the cloned project. If installed globally via pip, you can use the python -m form instead.
{
"mcpServers": {
"NotificationServer": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/mcp_server_notify",
"run",
"mcp-server-notify"
]
}
}
}MCP Notify Examples
Client configuration (Claude Desktop)
Full claude_desktop_config.json entry. Use the python -m form if mcp-server-notify is installed globally with pip.
{
"mcpServers": {
"NotificationServer": {
"command": "python",
"args": [
"-m",
"mcp_server_notify"
]
}
}
}Prompts to try
Add a notification request at the end of any task prompt. You can also configure this as a persistent rule in Cursor Settings so you never need to type it.
- "Refactor the authentication module to use JWT, then send me a notification when you are done"
- "Run all unit tests and fix any failures, then notify me with a desktop alert"
- "Generate a summary of all open GitHub issues, and finally send me a notification when the task is finished"
- "finally, send me a notification when task finished"Troubleshooting MCP Notify
Notifications do not appear on macOS
Confirm that terminal-notifier is installed ('which terminal-notifier'). Also check System Settings > Notifications to ensure notifications are allowed for Terminal or whichever app is running the Python process. Run 'python -m mcp_server_notify --debug' to see error details.
Notifications do not appear on Windows
pywin32 must be installed in the same Python environment used by the server ('pip install pywin32'). Also verify Windows Focus Assist is not silencing notifications. Run the server with '--debug' for detailed error output.
The MCP client says the server is not found or fails to start
Ensure the 'command' and path in your config file are absolute paths and that the virtual environment's Python or uv binary is used. Avoid relative paths. Restart the client after editing the config.
Frequently Asked Questions about MCP Notify
What is MCP Notify?
MCP Notify is a Model Context Protocol (MCP) server that 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. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Notify?
Follow the installation instructions on the MCP Notify GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Notify?
MCP Notify works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Notify free to use?
Yes, MCP Notify is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
MCP Notify Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to MCP 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 MCP 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 MCP Notify?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.