Skip to main content
Glama
leynier

MCP System Bridge

by leynier

send_notification

Read-only

Display native OS notifications with customizable title, message, app name, and timeout. Works on Windows, macOS, and Linux.

Instructions

Send a system notification.

Displays a native operating system notification with the specified title and message.
Works across Windows, macOS, and Linux platforms.

Args:
    title: The title of the notification (required)
    message: The message body of the notification (required)
    app_name: The name of the application sending the notification (optional)
    timeout: Duration in seconds to display the notification (default: 10)

Returns:
    A success message if the notification was sent successfully, or an error message if it failed.

Examples:
    send_notification("Task Complete", "Your build has finished successfully")
    send_notification("Warning", "Low disk space detected", app_name="System Monitor", timeout=5)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYes
messageYes
app_nameNo
timeoutNo

Implementation Reference

  • The `send_notification` tool handler function. It uses plyer's notification.notify() to display native OS notifications. Accepts title (required), message (required), app_name (optional), and timeout (optional, default 10s). Returns a success or error string.
    @mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))
    def send_notification(
        title: str,
        message: str,
        app_name: str | None = None,
        timeout: int = 10,
    ) -> str:
        """
        Send a system notification.
    
        Displays a native operating system notification with the specified title and message.
        Works across Windows, macOS, and Linux platforms.
    
        Args:
            title: The title of the notification (required)
            message: The message body of the notification (required)
            app_name: The name of the application sending the notification (optional)
            timeout: Duration in seconds to display the notification (default: 10)
    
        Returns:
            A success message if the notification was sent successfully, or an error message if it failed.
    
        Examples:
            send_notification("Task Complete", "Your build has finished successfully")
            send_notification("Warning", "Low disk space detected", app_name="System Monitor", timeout=5)
        """
        try:
            notification_params = {
                "title": title,
                "message": message,
                "timeout": timeout,
            }
    
            if app_name:
                notification_params["app_name"] = app_name
    
            notification.notify(**notification_params)
            return f"Notification sent successfully: '{title}'"
        except Exception as e:
            return f"Error sending notification: {e}"
  • src/server.py:53-53 (registration)
    The `send_notification` function is registered as an MCP tool via the `@mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))` decorator on line 53. This registers it with the FastMCP server instance.
    @mcp.tool(annotations=ToolAnnotations(readOnlyHint=True))
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description indicates a write operation ('Send', 'Displays') but the annotation declares readOnlyHint=true, creating a contradiction. No other behavioral traits (e.g., permissions, failure modes) are disclosed beyond the annotation's misalignment.

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 well-structured with Args, Returns, and Examples sections, making it easy to parse. It is slightly verbose with repeated info (e.g., 'required' in Args), but overall concise relative to the content provided.

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?

The description covers purpose, parameters, return value, and examples, which is adequate for a simple notification tool. However, it lacks error handling details and behavioral context, partly due to the annotation contradiction, reducing completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description fully compensates by explaining each parameter's role (e.g., 'title of the notification', 'message body', 'name of the application', 'Duration in seconds'). It adds defaults and examples, providing rich semantics beyond the schema's bare types.

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 clearly states 'Send a system notification' and 'Displays a native operating system notification', providing a specific verb and resource with cross-platform context. It is distinct from sibling tools like copy_to_clipboard, open_urls, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for sending notifications but does not explicitly state when to use this tool versus alternatives or provide exclusions. Sibling tools are distinct, so ambiguity is low, but no direct guidance is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

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/leynier/mcp-sys-bridge'

If you have feedback or need assistance with the MCP directory API, please join our Discord server