Paddle MCP Server

Official

Overview Schema Related Servers Score Discussions

replay_notification

Resend delivered or failed webhook notifications by ID to retry delivery for event-triggered notifications within 90 days.

Instructions

This tool will resend a delivered or failed notification, like a webhook notification, using its ID.

Don't use this tool without checking with the user first. Avoid using before gaining explicit approval.

Paddle creates a new notification entity for the replay, related to the same eventId. The response includes the new notificationId of the created notification.

Notifications older than 90 days aren't retained. If trying to replay a notification that's no longer retained, Paddle returns an error.

Only notifications with the origin of event can be replayed. Replaying a notification created for a replay isn't possible.

Check the following details to understand the success or failure of the notification according to Paddle and debug issues:

status: Status of the notification.
- notAttempted: Paddle hasn't yet tried to deliver this notification.
- needsRetry: Paddle tried to deliver this notification, but it failed. It's scheduled to be retried.
- delivered: Paddle delivered this notification successfully.
- failed: Paddle tried to deliver this notification, but all attempts failed. It's not scheduled to be retried.
origin: Describes how this notification was created.
- event: Notification created when a subscribed event occurred.
- replay: Notification created when a notification with the origin event was replayed.
deliveredAt: RFC 3339 datetime string of when this notification was delivered. null if not yet delivered successfully.
lastAttemptAt: RFC 3339 datetime string of when this notification was last attempted.
retryAt: RFC 3339 datetime string of when this notification is scheduled to be retried.
timesAttempted: How many times delivery of this notification has been attempted.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`notificationId`	Yes	Paddle ID of the notification.

Implementation Reference

src/functions.ts:551-562 (handler)

The main handler function that executes the tool logic by calling paddle.notifications.replay(notificationId) and handling errors.

export const replayNotification = async (
  paddle: Paddle,
  params: z.infer<typeof Parameters.replayNotificationParameters>,
) => {
  try {
    const { notificationId } = params;
    const notification = await paddle.notifications.replay(notificationId);
    return notification;
  } catch (error) {
    return error;
  }
};

src/api.ts:54-54 (registration)
Maps the tool method constant to the handler function in the toolMap used by PaddleAPI.run().
```
[TOOL_METHODS.REPLAY_NOTIFICATION]: funcs.replayNotification,
```

src/tools.ts:794-803 (schema)

Tool schema definition including input parameters (params.replayNotificationParameters), description, name, and required permissions/actions.

method: "replay_notification",
name: "Replay a notification",
description: prompts.replayNotificationPrompt,
parameters: params.replayNotificationParameters,
actions: {
  notifications: {
    write: true,
    create: true,
  },
},

src/constants.ts:46-46 (registration)
Constant definition for the tool method name used in registrations.
```
REPLAY_NOTIFICATION: "replay_notification",
```

src/prompts.ts:822-847 (helper)

Detailed prompt/description explaining the tool's purpose, warnings, and usage details.

export const replayNotificationPrompt = `
This tool will resend a delivered or failed notification, like a webhook notification, using its ID.

${checkBeforeWarning}

Paddle creates a new notification entity for the replay, related to the same eventId. The response includes the new notificationId of the created notification.

Notifications older than 90 days aren't retained. If trying to replay a notification that's no longer retained, Paddle returns an error.

Only notifications with the origin of event can be replayed. Replaying a notification created for a replay isn't possible.

Check the following details to understand the success or failure of the notification according to Paddle and debug issues:

- status: Status of the notification.
  - notAttempted: Paddle hasn't yet tried to deliver this notification.
  - needsRetry: Paddle tried to deliver this notification, but it failed. It's scheduled to be retried.
  - delivered: Paddle delivered this notification successfully.
  - failed: Paddle tried to deliver this notification, but all attempts failed. It's not scheduled to be retried.
- origin: Describes how this notification was created.
  - event: Notification created when a subscribed event occurred.
  - replay: Notification created when a notification with the origin event was replayed.
- deliveredAt: RFC 3339 datetime string of when this notification was delivered. null if not yet delivered successfully.
- lastAttemptAt: RFC 3339 datetime string of when this notification was last attempted.
- retryAt: RFC 3339 datetime string of when this notification is scheduled to be retried.
- timesAttempted: How many times delivery of this notification has been attempted.
`;

Tool Definition Quality

A4.4/5.0

Behavior4/5

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

The description adds significant behavioral context beyond the annotations (readOnlyHint: false, destructiveHint: false). It explains that a new notification entity is created, includes retention policies ('Notifications older than 90 days aren't retained'), error conditions, and detailed status/field explanations for debugging. While annotations indicate it's not read-only or destructive, the description provides operational details that help the agent understand the tool's effects and constraints.

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 and appropriately sized. It front-loads the core purpose and usage warnings, then provides detailed behavioral information. While somewhat lengthy due to the status/origin explanations, every section adds value for understanding the tool's operation and constraints, with no redundant or wasted sentences.

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?

Given the tool's complexity (mutation operation with specific constraints) and the absence of an output schema, the description provides comprehensive context. It explains what the tool does, when to use it, behavioral details (creation of new entity, retention limits, origin restrictions), and debugging information including status values and timestamps. This compensates well for the lack of structured output documentation.

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?

The input schema has 100% description coverage, with the single parameter 'notificationId' clearly documented as 'Paddle ID of the notification.' The description doesn't add additional parameter semantics beyond what's in the schema, but it provides context about what type of notification ID is acceptable (e.g., from delivered/failed notifications with origin 'event'). This meets the baseline for high schema 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 clearly states the tool's purpose with specific verbs ('resend a delivered or failed notification') and resources ('notification, like a webhook notification, using its ID'). It distinguishes itself from sibling tools by focusing on notification replay rather than creation or retrieval operations, which are covered by other tools like create_notification_setting, get_notification, and list_notifications.

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 provides explicit usage guidelines, including when to use ('resend a delivered or failed notification'), prerequisites ('Don't use this tool without checking with the user first. Avoid using before gaining explicit approval'), and exclusions ('Only notifications with the origin of event can be replayed. Replaying a notification created for a replay isn't possible'). This gives clear context for when and how to invoke the tool responsibly.

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

Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security
Open Source Has a Bot Problem
By punkpeye on March 19, 2026.
open source

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/PaddleHQ/paddle-mcp-server'

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