Skip to main content
Glama
pushengage-mcp

pushengage-mcp

Duplicate a notification

pushengage_duplicate_notification

Creates a new notification from an existing one, reusing its content, image, audience and UTM parameters; override any field and save the copy as a draft or send/schedule it.

Instructions

Creates a NEW notification from an existing one, reusing its content, image, audience and UTM parameters. Pass any field to change it in the copy. Works from a notification in any state, including one already sent or deleted — nothing about the original is modified, so copying a deleted one recovers its content. This is the way to "send that again but with a different title", where pushengage_resend_notification would send the original unchanged. The copy is saved as a DRAFT unless you pass status="sent" (dispatches immediately) or status="schedule" with a schedule_date. This differs from the dashboard's Duplicate button on purpose: the dashboard carries over the original's schedule, recurrence, subscriber-timezone setting and A/B shape, while this copies the CONTENT and audience only and leaves the timing to you — the original's date is in the past for anything already sent. Copying an A/B test therefore produces a plain notification from its A variant, not another test. Do not add optional fields unless the user explicitly asks to change them.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "notification_id": "<notification_id>"
    },
    "name": "pushengage_duplicate_notification"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoDestination URL when the subscriber clicks the notification
tagsNoUp to 5 tags, 36 chars each. Only when the user explicitly asks for tags.
titleNoNotification title
statusNoWhat to do with the copy. Defaults to "draft" so it is saved for review rather than dispatched — pass "sent" only when the user asks to send the copy now, or "schedule" with a schedule_date.draft
actionsNoAction buttons. Only when the user explicitly asks.
messageNoNotification message body
site_idNoOverride the currently selected site
ios_pushNoiOS-specific options. Only when the user explicitly asks.
expire_inNoExpiry in seconds (60–2419200). Only when the user explicitly asks.
image_urlNoSmall notification icon. Only when the user explicitly asks for an image.
utm_paramsNoUTM tracking params. Only when the user explicitly asks.
android_pushNoAndroid-specific options. Requires channel_id when set. Only when the user explicitly asks.
big_image_urlNoLarge hero image. Only when the user explicitly asks for a big image.
schedule_dateNoRequired when status is "schedule". Format: YYYY-MM-DD HH:mm:ss in the site timezone.
audience_groupsNoSend to one or more predefined audience groups (1-20 group IDs). Each ID refers to an audience group already configured in PushEngage. Omit this field to send to all subscribers. Only set this when the user mentions a saved/predefined audience group. Mutually exclusive with subscriber_filter.
notification_idYesThe notification to copy. Its content, image, audience and UTM parameters are reused; any field you pass overrides the copy.
schedule_timezoneNoOPTIONAL. The IANA timezone that `schedule_date` is written in, e.g. "Asia/Kolkata" or "America/New_York". Set this whenever the user names a timezone, or when you know their timezone differs from the site's — the notification is then scheduled for the instant they actually meant, and the response reports both wall clocks so you can tell them what was scheduled. Omit it and `schedule_date` is taken as the SITE's local time, which is what the API assumes. Requires schedule_date; cannot be combined with recurring_schedule, nor with send_in_subscribers_timezone (that flag already makes schedule_date each subscriber's own local time, so there is nothing to convert). Must be a full IANA zone name — abbreviations like "IST", "PST" or "EST" are ambiguous and are rejected, as are the Etc/GMT±N zones, whose sign is inverted.
subscriber_filterNoOPTIONAL. The dashboard's "Send to Custom Audience": personalize who receives this notification based on segments, location, device and more. Mutually exclusive with audience_groups; omit both for "Send to All Subscribers". A 2-D expression: `value` is a list of rule-groups, rules inside a group are AND-ed, and the top-level `op` combines the groups ("or" by default). Segment rules accept segment NAMES and are resolved automatically, so { field: "segments", op: "in", value: ["Sports Fans"] } works without a lookup. For country, state, city, device or device_type values call pushengage_list_audience_filter_values first; for an attributes rule's `key` call pushengage_list_attributes first. Both are site-specific, and a guessed value saves successfully but reaches the wrong people. Every segment reference and attribute key is verified before anything is sent; an unresolvable one fails the call rather than silently changing who receives the push. Example — mobile subscribers in the Sports Fans segment: { op: "or", value: [[{ field: "segments", op: "in", value: ["Sports Fans"] }, { field: "device", op: "in", value: ["mobile"] }]] }. Example — subscribed in the last 7 days on a paid plan: { op: "or", value: [[{ field: "ts_created", op: "ts_elapsed_lt", value: 10080 }, { field: "attributes", key: "plan", op: "ne", value: "free" }]] }.
recurring_scheduleNoOPTIONAL. Turns this into a recurring notification that fires on the chosen days/times between start_date and end_date. Mutually exclusive with status="schedule", schedule_date, and send_in_subscribers_timezone. With recurring_schedule set, leave status at "sent" (default) to activate the recurrence, or use "draft" to save without activating. Only set this when the user explicitly asks for a recurring/repeating notification.
send_in_subscribers_timezoneNoOnly valid when status="schedule" (and not combined with recurring_schedule). When true, schedule_date is interpreted in each subscriber's local timezone instead of the site timezone — one delivery is scheduled per subscriber timezone so every recipient receives the push at the same wall-clock time. Only set this when the user explicitly asks for subscriber-timezone delivery (for example: "send at 9am in their timezone").

Output Schema

NameRequiredDescriptionDefault
urlNo
titleNo
statusNo
messageNo
view_urlNo
notification_idNo
schedule_conversionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.2.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnly=false, destructive=false, idempotent=false, openWorld=true; the description adds substantial context beyond that: the original is never modified, a copy can be made from a sent or deleted notification (recovering content), the result is saved as a DRAFT by default unless status='sent' or 'schedule' with a date, and the dashboard's schedule/recurrence/subscriber-timezone/A/B shape are deliberately not carried over.

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?

It is front-loaded with the core action and each sentence carries distinct information (state independence, draft default, dashboard divergence, A/B behavior, the no-extra-fields rule). The prose is dense and em-dash heavy, and the clause justifying past dates is explanatory rather than actionable, so it is slightly longer than strictly needed.

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

Completeness5/5

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

For a 20-parameter, deeply nested tool with an output schema, the description covers the decisions an agent must make: what is copied vs overridden, the draft-by-default safety posture, how scheduling differs, and the A/B and deleted-notification edge cases. Return values are handled by the output schema, so nothing essential is missing.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds the override model as a whole — 'Pass any field to change it in the copy' — plus the status default semantics and the A/B caveat that copying a test yields a plain notification from its A variant. Small remaining gap: it doesn't call out schedule_timezone or subscriber_filter behavior, which the schema carries alone.

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 opens with a precise verb+resource: 'Creates a NEW notification from an existing one, reusing its content, image, audience and UTM parameters.' It explicitly separates this tool from pushengage_resend_notification ('would send the original unchanged') and from the dashboard's Duplicate button, so an agent can pick it without opening schemas.

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?

It names the exact scenario this tool serves ('send that again but with a different title') and the alternative when the original should go out unchanged. It also states an explicit exclusion: 'Do not add optional fields unless the user explicitly asks to change them,' plus status guidance for draft/sent/schedule.

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