Sends desktop notifications with an alert sound when an AI agent finishes a task.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent ā or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag ā we're steadily working through the catalog.
š” Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by MCP Server Notify.
Cactusinhand/mcp_server_notify MCP server gives an agent a way to notify the user through the local desktop when a task is complete. Notifications include a sound effect, and the project includes the sound file used for the alert. The intended workflow is to add an instruction such as asking the agent to notify you after finishing a task, then let the agent invoke the notification capability.
The server is designed for desktop environments rather than hosted notification delivery. It supports Windows, macOS, and Linux, and follows the standard Model Context Protocol so it can be configured in MCP-compatible clients.
The package runs as a local Python MCP process. Desktop notification delivery is implemented through the Apprise API, while the MCP client exposes the notification action to the agent. In VS Code with Copilot agent mode, the README identifies the action as send_notification; equivalent client behavior depends on how the MCP client presents server tools.
After the server is registered with a client, an agent can call the notification action when it reaches a completion point. For Cursor, the README suggests adding a completion instruction to prompts or configuring it as a rule. The server does not provide Docker support because native host notification access is not currently available from the project's Docker setup.
Install the package from PyPI with either uv pip install mcp-server-notify or pip install mcp-server-notify. The module can be started with python -m mcp_server_notify. It also accepts --debug and a --file option for logging; the documented example uses --log-file=path/to/logfile.log.
For clients that support uvx, the package can be launched with uvx mcp-server-notify. Claude Desktop and Cursor examples instead show a local uv configuration using the project directory and uv run mcp-server-notify, or a Python module configuration using python -m mcp_server_notify.
Platform dependencies may be required. Windows needs pywin32. macOS needs the terminal-notifier utility installed through Homebrew. The README does not list an additional desktop dependency for Linux.
send_notification in the VS Code usage instructions.Cactusinhand/mcp_server_notify MCP server depends on the desktop environment being able to receive native notifications. The required setup differs by operating system, so a successful Python package installation alone may not be sufficient on Windows or macOS.
Docker is documented as unavailable because containers are isolated from host operating-system notification facilities and the project would need to handle different native notification systems and dependencies. The provided material does not document remote hosting, authentication, notification history, or delivery to external messaging services. Cactusinhand/mcp_server_notify MCP server is licensed under MIT.
Factual signals from GitHub, npm, and our automated checks ā not a rating.
No reviews yet ā be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/cactusinhand-mcp-server-notify)<a href="https://allmcps.com/mcp/cactusinhand-mcp-server-notify"><img src="https://allmcps.com/api/badge/cactusinhand-mcp-server-notify?style=directory" alt="MCP Server Notify on AllMCPs" /></a>