Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Pocket Alert 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%2Fpocketalert.app%2Fpocketalert" | 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%2Fpocketalert.app%2Fpocketalert" | 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 Pocket Alert API.
Push a notification with a title and message to every device on the account, or to one device by device_id
Set the delivery level from silent through critical, where critical bypasses Do Not Disturb on paid plans
Attach up to three action buttons of type view, http, or copy, and an image attachment
Schedule a notification with send_at up to 30 days ahead or a relative delay such as 30m, and cancel a pending scheduled message
GET STARTED
Check today's usage, the daily limit, rejected requests, and when the count resets
Create inbound webhook receivers that turn JSON posted by third-party services into notifications, and read their recorded request history
Organise notifications into application channels and rename or remove registered devices
Patterns agents use Pocket Alert API for, with concrete tasks.
★ Agent Status Alerts via Jentic
A coding or ops agent running a long job needs to tell its owner when something finishes or fails. Through Jentic it calls the Pocket Alert sendMessage operation with a title, a message, and a level such as high, so the developer's phone buzzes with the result instead of the developer watching a terminal, and it can check getMessageUsage first to stay inside the daily limit.
Check getMessageUsage, then send a notification titled 'Deploy finished' with message 'v1.4.2 is live', level high, and a view action linking to the dashboard
Turning Monitoring Webhooks into Phone Alerts
Developers who want alerts from uptime monitors, CI, or payment events create a webhook receiver with a name and a message template. Third-party services post JSON to the receiver's p4a.me URL, Pocket Alert renders it into a notification, and getWebhookHistory shows the recorded inbound requests when a trigger needs debugging.
Create a webhook receiver named 'Uptime' with a message template and default_level 1, then read its history to confirm the first inbound request arrived
Scheduled Reminders
On paid plans a notification can be stored and delivered later using send_at as an RFC 3339 time, Unix seconds, or a local date and time, or with a relative delay such as 2h. Pending scheduled messages can be listed by status and cancelled before they fire.
Send a notification titled 'Standup' with send_at '2026-11-12T09:00:00Z', then list scheduled messages to confirm it is pending
35 endpoints — the pocket alert api sends push notifications to the phones on a pocket alert account with a single request carrying a title and a message.
METHOD
PATH
DESCRIPTION
/v1/messages
Send a push notification
/v2/messages
List messages, paginated
/v1/messages/usage
Read today's usage against the daily limit
/v1/messages/scheduled
List scheduled messages
/v1/messages/scheduled/{tid}
Cancel a pending scheduled message
/v1/webhooks
Create a webhook receiver
/v1/devices
List registered devices
/v1/applications
Create an application channel
/v1/messages
Send a push notification
/v2/messages
List messages, paginated
/v1/messages/usage
Read today's usage against the daily limit
/v1/messages/scheduled
List scheduled messages
/v1/messages/scheduled/{tid}
Cancel a pending scheduled message
/v1/webhooks
Create a webhook receiver
/v1/devices
List registered devices
/v1/applications
Create an application channel
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Pocket Alert by hand means picking between a Token header API key and a JWT from the sign-in operation, tracking the daily message limit, and learning which fields only work on paid plans. Through Jentic you install once, import Pocket Alert from the API Directory, store the key once, and your agent sends notifications.
Permission scoping
Pocket Alert puts the message, application, device, and webhook ids in the URL path (/v1/messages/{tid}, /v1/webhooks/{tid}), so a rule can pin your agent to one webhook receiver or one message. Sending takes its target device in the request body, so for sends rules bound the operation rather than the device. You choose the operations it may call, so bulk deletion and API key revocation are not included unless you add them.
Credential isolation
Your Pocket Alert API key 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 push notification to my phone' or 'check my notification usage', and Jentic returns the matching Pocket Alert 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 Pocket Alert API through Jentic.
What authentication does the Pocket Alert API use?
The Pocket Alert API declares two schemes in its OpenAPI spec: an API key sent as an apiKey in the Token header, created on your Pocket Alert account's API keys page, or a JWT sent as a bearer token in the Authorization header, obtained from the sign-in operation at /v1/auth/signin. The sign-in operation itself is open. Through Jentic the API key is stored encrypted on your own instance and injected at call time.
Is there a Pocket Alert MCP server?
You don't need an MCP server to give your agent Pocket Alert. Jentic connects it directly from the API Directory: import Pocket Alert, store your API key once, and your agent can send notifications straight away. Operations are discovered on demand, so no extra server's tool definitions sit in your agent's context.
Can I limit what my agent is allowed to do with the Pocket Alert API?
Yes. Write a rule that allows only sendMessage and getMessageUsage, so the agent can notify you and check the daily count but cannot delete every message, revoke API keys, or remove devices, and the calls it makes are logged.
What are the rate limits for the Pocket Alert API?
Per the OpenAPI spec, Pocket Alert applies a daily message limit set by your plan: each accepted send counts toward it and rejected ones do not. The getMessageUsage operation returns used, limit, rejected, and resets_at, and limit is null on unlimited plans. See https://pocketalert.app for plan limits.
Which Pocket Alert features need a paid plan?
Per the spec, scheduling with send_at or delay, image attachments, action buttons, and the critical delivery level are paid features. On free plans action buttons are dropped and critical is delivered as high.
How do I send a push notification with the Pocket Alert API through Jentic?
Search Jentic for an intent like 'send a push notification to my phone', import Pocket Alert, and store your API key once. Your agent then calls sendMessage at /v1/messages with a title and message, plus an optional device_id, level, or application_id. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Send push notifications to your own phones with a title, message, level, actions, and optional schedule, and track daily usage against the plan limit. Also manages channels, devices, webhook receivers, forms, and API keys.
Use for: I need to send a push notification to my phone when the deploy finishes, Send a critical alert that bypasses Do Not Disturb, Schedule a reminder notification for tomorrow at 9am, Check how many notifications I have left today
Not supported: Does not handle SMS, email delivery, or push campaigns to an app's end users. Use for sending notifications to the account owner's own devices only.
The Pocket Alert API sends push notifications to the phones on a Pocket Alert account with a single request carrying a title and a message. A notification can target one device or all of them, file under an application channel, set a delivery level from silent to critical, carry up to three action buttons, attach an image, or be scheduled with send_at or delay on paid plans. The API also lists, reads, marks, and deletes messages, reports daily usage against the plan's message limit, and manages applications, devices, inbound webhook receivers that turn third-party JSON into notifications, forms, and API keys.
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>