Skip to main content
Glama

Ntfy Push Notification

ntfy_send_notify

Send push notifications to devices using Ntfy. Customize message, title, priority, actions, and schedule delivery.

Instructions

Push a notification via Ntfy

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
messageYesNotification message body; set to `triggered` if empty or not passed
titleNoNotification title
topicNoTarget topic name or URL
clickNoURL opened when notification is clicked
attachNoURL of an attachment
iconNoURL of notification icon
markdownNoSet to `true` if the message is Markdown-formatted
filenameNoFile name of the attachment
priorityNoMessage priority with 1=min, 3=default and 5=max
delayNoTimestamp or duration for delayed delivery. Example: 30min, 9am
actionsNoList of action buttons. The following actions are supported: - view: Opens a website or app when the action button is tapped - broadcast: Sends an Android broadcast intent when the action button is tapped (only supported on Android) - http: Sends HTTP POST/GET/PUT request when the action button is tapped ```json [ { "action": "view", "label": "Open portal", "url": "https://home.nest.com/", "clear": true }, { "action": "http", "label": "Turn down", "url": "https://api.nest.com/", "body": "{"temperature": 65}" }, { "action": "broadcast", "label": "Take picture", "extras": { "cmd": "pic", "camera": "front" } } ] ```

Implementation Reference

  • Handler function for the ntfy_send_notify tool. Sends a push notification via ntfy.sh using the HTTP API. Accepts message, title, topic, click URL, attachment, icon, markdown flag, filename, priority, delay, and action buttons. Constructs a JSON payload and POSTs it to the ntfy base URL (default https://ntfy.sh, configurable via NTFY_BASE_URL env var).
    def ntfy_send_notify(
        message: str = Field(description="Notification message body; set to `triggered` if empty or not passed"),
        title: str = Field("", description="Notification title"),
        topic: str = Field("", description="Target topic name or URL"),
        click: str = Field("", description="URL opened when notification is clicked"),
        attach: str = Field("", description="URL of an attachment"),
        icon: str = Field("", description="URL of notification icon"),
        markdown: bool = Field(False, description="Set to `true` if the message is Markdown-formatted"),
        filename: str = Field("", description="File name of the attachment"),
        priority: int = Field(3, description="Message priority with 1=min, 3=default and 5=max"),
        delay: str = Field("", description="Timestamp or duration for delayed delivery. Example: 30min, 9am"),
        actions: list | None = Field(None, description=f"List of action buttons.{NTFY_ACTIONS_RULE}"),
    ):
        """
        https://docs.ntfy.sh/publish/#publish-as-json
        """
        base = os.getenv("NTFY_BASE_URL") or "https://ntfy.sh"
        if topic and topic.startswith("http"):
            base, topic = topic.rsplit("/", 1)
        if not topic:
            topic = os.getenv("NTFY_DEFAULT_TOPIC", "")
        data = {
            "topic": topic,
            "title": title,
            "message": message,
            "click": click,
            "icon": icon,
            "markdown": markdown or False,
            "priority": priority,
            "delay": delay,
        }
        if attach:
            data["attach"] = attach
            data["filename"] = filename
        if actions:
            data["actions"] = actions
        res = requests.post(f"{base}", json=data)
        return res.json()
Behavior2/5

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

With no annotations, the description carries full burden, but only states 'Push a notification via Ntfy'. It does not disclose behavioral traits such as authentication requirements, error behavior, or side effects, offering minimal transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. It is appropriately sized for the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite 11 parameters and no output schema, the description is too brief. It lacks an overview of how to use the tool effectively, such as example usage or notes on required configurations like topic.

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

Parameters3/5

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

Schema coverage is 100%, with detailed parameter descriptions. The tool description adds no new information about parameters beyond what the schema provides, meeting the baseline for high coverage.

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 'Push a notification via Ntfy' clearly specifies the action (push) and the resource (notification via Ntfy). It distinguishes the tool from siblings like bark_send_notify or wework_send_text by naming the service.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool over siblings. The description does not mention context, limitations, or alternatives, leaving the agent to infer usage solely from the tool name.

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/aahl/mcp-notify'

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