Allows sending push notifications to your phone via ntfy, with customizable title, priority, tags, and click URL.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ntfy-notify Send a job alert: found 5 new listings"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A tiny Model Context Protocol (MCP) server that lets Claude / Cowork push notifications to your phone via ntfy. Point a scheduled task at it and the results land on your lock screen instead of waiting in a log somewhere.
Why I built this: I run a scheduled daily job-search inbox sweep, and I wanted the summary on my phone the moment it finishes instead of having to go check on it. ntfy is a dead-simple pub/sub-over-HTTP service, so the whole thing is one HTTP POST behind an MCP tool.
Exposes two MCP tools over stdio:
Tool | Purpose |
| Send any push notification to your configured ntfy topic. |
| Convenience wrapper: title "Job sweep", high priority, briefcase tag. |
priority accepts min / low / default / high / urgent (or "1".."5").
tags is a comma-separated list of emoji shortcodes,
e.g. tada,computer. click_url opens when you tap the notification.
Related MCP server: ntfy-mcp
ntfy is pub/sub over HTTP. You pick a topic — any string — and subscribe to it in the phone app. Anyone who knows the topic name can publish to it with a single HTTP POST, and it shows up on every subscribed device. There's no account or auth for public topics, which means the topic name is the only secret, so make it long and random.
There's no daemon and no always-on process. A stdio MCP server is launched by the client (Claude/Cowork) as a child process when a session starts, speaks JSON-RPC over stdin/stdout, stays idle until a tool is called, and is shut down when the session ends.
Claude / Cowork session
│ (launches as subprocess, JSON-RPC over stdio)
▼
server.py ──► @mcp.tool() functions
│ send_notification / send_job_alert
│ builds one HTTP POST:
│ body = message text
│ headers = Title / Priority / Tags / Click / Authorization
▼
https://ntfy.sh/<NTFY_TOPIC>
│ (pub/sub fan-out)
▼
ntfy app on your phoneKey design points:
The topic is read from the environment, never hardcoded (_config()). Since
the topic name is the only secret in ntfy, this is what makes the repo safe to
be public — and it fails loudly with a clear error if NTFY_TOPIC is unset.
@mcp.tool() turns a plain function into a tool. The function name, type
hints, and docstring become the schema and description that Claude reads to
decide when and how to call it.
ntfy has no JSON payload. The message is the raw request body; everything else (title, priority, tags, click URL, auth token) rides along as HTTP headers.
Every call returns an OK: / FAILED: status string so the model knows
whether the push actually went out. Network errors and non-2xx responses are
caught and reported rather than raised.
Run the test suite (pure logic + header construction, no network calls):
pip install -e ".[dev]"
pytestInstall ntfy on your phone:
Android: Play Store or F-Droid
Generate a long, random topic name so nobody else can guess it:
openssl rand -hex 16In the app, tap + and subscribe to that exact string.
Requires Python 3.10+.
git clone https://github.com/Gardner-Programs/ntfy-notify.git
cd ntfy-notify
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txtCopy the example and fill it in:
cp .env.example .envVariable | Required | Default | Notes |
| yes | — | Your long, random topic. Never hardcoded. |
| no |
| Set to your own host if self-hosting. |
| no | — | Bearer token for protected / self-hosted topics. |
The server reads these from the process environment. The MCP config below sets
them directly, so a .env file is only needed for the curl test / manual runs.
Add an entry to your MCP client config. For Claude Desktop
(claude_desktop_config.json) or Cowork, point it at the cloned repo:
{
"mcpServers": {
"ntfy-notify": {
"command": "python",
"args": ["/absolute/path/to/ntfy-notify/server.py"],
"env": {
"NTFY_TOPIC": "your-long-random-topic",
"NTFY_BASE_URL": "https://ntfy.sh",
"NTFY_TOKEN": ""
}
}
}
}For Claude Code, the equivalent one-liner:
claude mcp add ntfy-notify \
--env NTFY_TOPIC=your-long-random-topic \
-- python /absolute/path/to/ntfy-notify/server.pyIf you installed into a virtualenv, use that interpreter's absolute path (e.g.
/absolute/path/to/ntfy-notify/.venv/bin/python) as thecommand.
Restart the client and the send_notification / send_job_alert tools will appear.
You don't need this server to test ntfy itself — confirm your topic works first:
curl \
-H "Title: Hello from ntfy" \
-H "Priority: high" \
-H "Tags: tada" \
-d "It works!" \
https://ntfy.sh/your-long-random-topicWith a token (protected / self-hosted):
curl \
-H "Authorization: Bearer tk_yourtoken" \
-d "It works!" \
https://ntfy.example.com/your-long-random-topicYou should get a push on your phone within a second or two.
Once the server is registered, update the scheduled daily-job-inbox-sweep task so its final step calls the tool with the run's summary, e.g.:
At the end of the run, call
send_job_alertwith a one-paragraph summary of what was found (new postings, replies, anything needing action).
send_job_alert already sets a sensible title and high priority, so a single call
with the summary text is all the task needs.
MIT — see LICENSE.
Send a job-search inbox-sweep summary with sensible defaults.
Thin wrapper around send_notification: title "Job sweep", high priority, a briefcase tag. Intended for the daily job-inbox-sweep task.
Args: summary: The summary text to push to your phone.
Returns: A status string starting with "OK:" on success or "FAILED:" on error.
| Name | Required | Description | Default |
|---|---|---|---|
| summary | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: it is a thin wrapper with fixed defaults (title 'Job sweep', high priority, briefcase tag), and it specifies the return format (status string starting with 'OK:' or 'FAILED:'). No hidden behaviors or contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise, uses bullet-like Args/Returns sections, and front-loads the purpose. Every sentence adds value with no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and an output schema (which it describes), the description covers purpose, usage, behavior, parameter meaning, and return format. No gaps given the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% description coverage, but the description adds 'summary: The summary text to push to your phone.' While this is basic, it provides meaning beyond the parameter name and type. Could include constraints like max length, but the meaning is clear.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool sends a 'job-search inbox-sweep summary with sensible defaults', identifies it as a thin wrapper around send_notification, and specifies the defaults. This distinguishes it from the sibling tool and leaves no ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly says 'Intended for the daily job-inbox-sweep task', providing clear context. It identifies the parent tool (send_notification) but does not explicitly state when not to use it. The guidance is adequate but lacks explicit alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Send a push notification to the configured ntfy topic (your phone).
Args: message: The notification body text. title: Optional bold title shown above the message. priority: One of min, low, default, high, urgent (or "1".."5"). Anything unrecognized falls back to "default". tags: Comma-separated emoji shortcodes, e.g. "tada,computer". click_url: Optional URL opened when the notification is tapped.
Returns: A status string starting with "OK:" on success or "FAILED:" on error.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | ||
| title | No | ||
| message | Yes | ||
| priority | No | default | |
| click_url | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility. It only states that a notification is sent and returns a status string. Missing details: whether the tool blocks, rate limits, side effects, or what happens if the ntfy topic is unreachable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise: one sentence for purpose, then bullet-like Args and Returns. No wasted words. Front-loaded with the main action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema (implied by context) and 5 parameters, the description covers parameter semantics and return status well. It lacks prerequisites (ntfy configuration) and error handling details, but overall is sufficient for a straightforward notification tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description compensates fully by explaining every parameter's meaning. For 'priority' it enumerates valid values and fallback. 'tags' is described as 'emoji shortcodes'. 'click_url' and 'title' are defined. This adds high value beyond the schema's bare names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description opens with 'Send a push notification to the configured ntfy topic (your phone).' The verb 'Send' and resource 'push notification' with a specific target (ntfy topic) clearly define the action. This distinguishes it from 'send_job_alert' which likely targets a different channel.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus the sibling 'send_job_alert'. There is no mention of prerequisites (e.g., ntfy must be configured) or scenarios where alternatives should be considered.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools have clear, distinct purposes: send_notification for general push notifications and send_job_alert as a specialized wrapper for job search alerts. No overlap or ambiguity.
Both tool names follow a consistent verb_noun pattern (send_job_alert, send_notification), making them predictable and intuitive.
With 2 tools, the set is minimal but well-justified: a general notification tool and a convenience wrapper for a common use case. A few more specific wrappers could be added, but current count is appropriate for the server's focused purpose.
The server's purpose is to send push notifications, and it provides both a general-purpose tool and a task-specific shortcut. There are no obvious gaps for the intended functionality.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Push notifications for AI agents - send instant iPhone notifications from any MCP client.
Push notifications with personalized sounds - manage and trigger your vybits via MCP
Let your AI agent notify you by email, Slack, Discord, or webhook. One tool: send_notification.
Let agents send content-free push notifications to a paired phone via MCP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Gardner-Programs/ntfy-notify'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
