ntfy-mcp

Overview Schema Source Related Servers Discussions Admin

Update a notification

update_message

DestructiveIdempotent

Revise a published notification in place, replacing its content so subscribers see the update without receiving a duplicate.

Instructions

Replaces the content of a notification already published, so subscribers see it change in place instead of receiving another one.

The sequence id is the id returned by publish_message. It only exists for cached messages: one published with "cache": false cannot be updated. Only the fields given are sent; the cache keeps each revision as its own entry pointing back at the original, which is why list_messages shows them with an "updates" field — the original keeps its old text and a second entry carries the new one.

Needs ntfy 2.16.0 or newer, and the failure below that is silent: an older server simply publishes a new notification instead of revising the old one, and answers success. If subscribers report receiving two, that is why — check get_server_info for the version.

Asks a person first; where the client cannot show a dialog, call once to receive a token and again with it.

Input Schema

TableJSON Schema

Name	Required	Description
`icon`	No	URL of a JPEG or PNG icon.
`tags`	No	Tags as separate entries. Names that match an emoji short code (for example "warning", "rocket") are rendered as that emoji.
`click`	No	URL opened when the notification itself is tapped.
`title`	No	The notification title.
`topic`	No	Its topic. Defaults to the first NTFY_TOPICS entry.
`actions`	No	Up to 3 action buttons. An "http" action fires from the recipient's device, not from the server, and defaults to POST.
`message`	No	The notification body.
`markdown`	No	Render the message as Markdown in clients that support it.
`priority`	No	1 (min) to 5 (max), or "min"/"low"/"default"/"high"/"max".
`sequence_id`	Yes	Id of the notification to revise, as returned by publish_message.
`confirm_token`	No	The token from this tool’s previous, unconfirmed response.

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No	Set when the revision landed but the id did not.
`topic`	Yes
`updated`	Yes	The sequence id that was revised.
`revision_id`	No	Id of the revision entry the cache now also holds.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.3.0Sep 8, 2026

addedOutput schema / properties / note

Added value: +{
+  "description": "Set when the revision landed but the id did not.",
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "topic",
-  "updated",
-  "revision_id"
-]New value: +[
+  "topic",
+  "updated"
+]

First observedv0.2.0Sep 5, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the annotations, the description discloses important behavior: only provided fields are updated, cache revisions are stored as separate entries linked to the original, and the tool asks a person for confirmation first. It also warns about silent fallback to publishing a new notification on older servers.

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 front-loaded with the core purpose and then adds necessary caveats. It is longer than the ideal two-sentence example, but each paragraph earns its place by covering confirmation flow, cache behavior, and version compatibility.

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

Completeness4/5

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

Given the tool's complexity—11 parameters, action variants, and annotations—the description is largely complete. It covers the main behavioral constraints and confirmation flow, though it does not elaborate on every action-variant field; the schema carries most of that detail.

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

Parameters4/5

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

The schema already covers 100% of parameters with descriptions, so the baseline is 3. The description adds useful cross-parameter meaning: sequence_id comes from publish_message, only cached messages can be updated, and only provided fields are sent, which aids correct use of the optional fields.

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 states a specific verb and resource: it replaces the content of an already published notification. It also distinguishes this from publishing a new notification by explaining that subscribers see the change in place rather than receiving another one.

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

Usage Guidelines5/5

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

The description explicitly says when to use the tool: only for cached messages with a sequence id returned by publish_message, and not for messages published with cache=false. It also gives a version requirement and explains the silent failure mode on older ntfy servers, plus the confirmation-token flow.

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

Deploy Server