Pushbullet API
✓ Official Vendor SpecCommunicationsPush NotificationsapiKey21 EndpointsREST
For Agents
Programmatically get current user, create devices. Covers 21 operations with apiKey authentication.
Use for: I need to current user, I want to devices, Search for devices, Find all devices
Not supported: Does not handle payments, crm, or developer tools - use for communications only.
Pushbullet push notification and messaging API. The API exposes 21 endpoints secured with apiKey authentication.
Install Jentic One Beta
Connect the Pushbullet API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Pushbullet 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.
1
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%2Fpushbullet.com%2Fpushbullet" | sh2
Step 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%2Fpushbullet.com%2Fpushbullet" | 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.
Capabilities
What an agent can do with Pushbullet API.
Get current user
Create Devices
List Devices
Update Devices
Delete Devices
Use Cases
Patterns agents use Pushbullet API for, with concrete tasks.
★ Communications Operations
Use the Pushbullet API to perform communications operations programmatically. The API provides 21 endpoints covering core functionality including get current user, create devices, list devices.
Call GET /v2/users/me to get current user
Automated Channel Info Management
Automate channel info operations by combining multiple Pushbullet API endpoints. Agents can create devices and then list devices in a single workflow.
Call POST /v2/devices to create devices, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Pushbullet API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.
Search Jentic for 'get current user', load the operation schema, and execute with Jentic-managed credentials
Key Endpoints
21 endpoints — pushbullet push notification and messaging api.
METHOD
PATH
DESCRIPTION
GET
/v2/users/me
Get current user
POST
/v2/devices
Create Devices
GET
/v2/devices
List Devices
GET
/v2/devices/{iden}
Get Devices
PUT
/v2/devices/{iden}
Update Devices
DELETE
/v2/devices/{iden}
Delete Devices
POST
/v2/pushes
Create push
GET
/v2/pushes
List pushes
GET
/v2/users/me
Get current user
POST
/v2/devices
Create Devices
GET
/v2/devices
List Devices
GET
/v2/devices/{iden}
Get Devices
PUT
/v2/devices/{iden}
Update Devices
DELETE
/v2/devices/{iden}
Delete Devices
POST
/v2/pushes
Create push
GET
/v2/pushes
List pushes
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Pushbullet by hand means sending its Access-Token header on every request and handling device and push calls yourself. Through Jentic you install once, import the Pushbullet API from the API Directory, store the token once, and your agent calls it.
Permission scoping
Pushbullet puts the device id in the URL path (/v2/devices/{iden}), so a rule can pin your agent to one device: it can read or update that device and nothing else. You choose the operations it may call, so device deletion is not included unless you add it.
Credential isolation
Your Pushbullet 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 push' or 'list my devices', and Jentic returns the matching Pushbullet operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Pushbullet API through Jentic.
What authentication does the Pushbullet API use?
The Pushbullet API uses an API key passed in the `Access-Token` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I get current user with the Pushbullet API?
Yes. Use the GET /v2/users/me endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Pushbullet API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I get current user through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'get current user'. Jentic returns the matching Pushbullet API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Pushbullet API have?
The Pushbullet API exposes 21 endpoints covering channel info, chats, devices operations.
Can I limit what my agent is allowed to do with the Pushbullet API?
Yes. Because you run Jentic One yourself, your own rules decide which Pushbullet operations and credentials the agent may use. Pushbullet puts the device id in the URL path (/v2/devices/{iden}), so a rule can pin your agent to a single device and let it read or update only that one. You also choose which operations are allowed, so an action like DELETE /v2/devices/{iden} stays off limits unless you explicitly grant it.
GET STARTED