Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Pushpad API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpushpad.xyz%2Fpushpad" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fpushpad.xyz%2Fpushpad" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Pushpad API.
Send a web push notification to a project with title, body, target_url, image_url, and action buttons
Schedule a notification for later with send_at and cancel it before it goes out
Target delivery at specific users or segments with uids and tags
Read delivery stats such as successfully_sent_count, opened_count, and scheduled_count for a notification
GET STARTED
List, tag, and delete browser subscriptions within a project
Create projects tied to a sender and manage VAPID senders with their key pairs
Patterns agents use Pushpad API for, with concrete tasks.
★ Agent-sent push alerts through Jentic
An operations agent sends a web push alert when something needs attention, such as a price drop or a status change. Through Jentic it calls the Pushpad send operation for one project, the developer's own Jentic One instance injects the bearer token, and a rule pinned to that project id keeps it from touching other projects.
POST /projects/123/notifications with body 'Your order has shipped', title 'Order update', and target_url 'https://example.com/orders/987'
Scheduled campaign notifications
Marketing sends land best at the right hour. The send operation accepts send_at to schedule a notification, the scheduled flag shows it is pending, and DELETE /notifications/{notification_id}/cancel withdraws it if plans change.
POST /projects/123/notifications with body 'Sale starts now' and send_at '2026-11-20T09:00:00Z', then DELETE /notifications/{notification_id}/cancel if the sale is postponed
Segmented delivery by user and tag
Not every notification is for everyone. Subscriptions carry a uid and tags, and a notification can target uids or tags so only matching browsers receive it, for example a one-to-one alert for a logged-in user or a broadcast to a 'beta' segment.
PATCH /projects/123/subscriptions/{subscription_id} to add the tag 'beta', then POST /projects/123/notifications with tags ['beta'] and body 'Try the new feature'
Delivery and engagement reporting
After a send, GET /notifications/{notification_id} returns counts including successfully_sent_count and opened_count, so an agent can report how a notification performed or compare recent sends listed for the project.
GET /projects/123/notifications, then GET /notifications/{notification_id} for each and report successfully_sent_count and opened_count
19 endpoints — the pushpad api sends web push notifications to the browsers subscribed to a pushpad project and reports how many were delivered and opened.
METHOD
PATH
DESCRIPTION
/projects/{project_id}/notifications
Send a new notification
/projects/{project_id}/notifications
List latest notifications
/notifications/{notification_id}
Get a notification with stats
/notifications/{notification_id}/cancel
Cancel a scheduled notification
/projects/{project_id}/subscriptions
List subscriptions
/projects/{project_id}/subscriptions/{subscription_id}
Update a subscription
/projects
Create a project
/projects/{project_id}/notifications
Send a new notification
/projects/{project_id}/notifications
List latest notifications
/notifications/{notification_id}
Get a notification with stats
/notifications/{notification_id}/cancel
Cancel a scheduled notification
/projects/{project_id}/subscriptions
List subscriptions
/projects/{project_id}/subscriptions/{subscription_id}
Update a subscription
/projects
Create a project
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Pushpad by hand means creating an access token, sending it as a bearer header, and tracking project and notification ids across calls yourself. Through Jentic you install once, import Pushpad from the API Directory, store the token once, and your agent calls it.
Permission scoping
Pushpad puts the project id in the URL path (/projects/{project_id}/notifications), so a rule can pin your agent to one project: it can send and list notifications for that site and nothing else. You choose the operations it may call, so destructive ones like project deletion or sender deletion are not included unless you add them.
Credential isolation
Your Pushpad access token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'send a web push notification' or 'cancel a scheduled notification', and Jentic returns the matching Pushpad operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Pushpad API through Jentic.
What authentication does the Pushpad API use?
The Pushpad API declares an HTTP bearer scheme (BearerAuth) in its OpenAPI spec: you create an access token in Pushpad's account settings and send it as Authorization: Bearer. Through Jentic, the token is stored encrypted by your own Jentic One instance and injected at execution time.
Can I schedule a notification with the Pushpad API?
Yes. Include send_at when you POST /projects/{project_id}/notifications and the notification is held until that time. While it is pending you can cancel it with DELETE /notifications/{notification_id}/cancel.
What are the rate limits for the Pushpad API?
The OpenAPI spec defines a rate-limit-exceeded error response but does not state the numeric limit. Check the Pushpad documentation at https://pushpad.xyz/docs for current limits.
How do I send a push notification with the Pushpad API through Jentic?
Install Jentic One, import the Pushpad API from the Jentic API Directory, and store your access token. Your agent searches for 'send a web push notification', Jentic returns POST /projects/{project_id}/notifications with its schema, and the agent calls it with a body and optional title and target_url. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a Pushpad MCP server?
You don't need an MCP server to give your agent Pushpad. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it, discovering operations on demand rather than loading every tool definition into its context.
Can I limit what my agent is allowed to do with the Pushpad API?
Yes. Write a rule that allows only POST and GET on /projects/123/notifications plus GET /notifications/{notification_id}, so the agent can send to project 123 and read the results, while deleting projects, senders, or subscriptions stays out of reach. Every call it makes is logged.
For Agents
Send or schedule web push notifications to a Pushpad project, target them by uid or tag, cancel scheduled sends, and manage subscriptions, projects, and senders.
Use for: I want to send a push notification to everyone subscribed to my site, Schedule a push notification for tomorrow morning, Send a notification only to users tagged 'beta', Check how many people opened yesterday's notification
Not supported: Does not handle email, SMS, or native mobile app push. Use for browser web push notifications and their subscriptions only.
The Pushpad API sends web push notifications to the browsers subscribed to a Pushpad project and reports how many were delivered and opened. A notification can carry a title, body, target_url, images, action buttons, and a send_at time for scheduling, and can be targeted at specific uids or tags. The API also manages the subscriptions, projects, and VAPID senders behind those notifications.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>