How to Use the Pushbullet MCP in Google ADK

Q: Can my Google ADK agent read my Pushbullet channel subscriptions?

Yes, your agent calls listchannelsubscriptions to pull feed data directly into Gemini's context window. You also use subscribetochannel to programmatically join new channels based on BigQuery data.

Q: How does Google ADK handle authentication with Pushbullet?

The ADK passes your Vinkius endpoint token securely to run testpushbulletauth at startup. This validates your credentials before the agent attempts to execute listconnecteddevices.

Q: Can I restrict which Pushbullet tools are exposed to my Google ADK agent?

Yes, you use the optional toolnames filter in McpToolset to limit access. This lets you expose sendpushnotification while blocking dangerous tools like removedevice.

Push alerts and links from your Google ADK workflows to any phone using send_push_notification and Gemini models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Pushbullet MCP to Google ADK

Create your Vinkius account to connect Pushbullet to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Pushbullet with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Device Push Routing with Google ADK

This Pushbullet integration lets your Gemini-powered agent call `list_connected_devices` to map out your hardware targets. The model processes this list within its massive context window and dispatches alerts via `send_push_notification` directly to your phone. By building on the Google ADK, you feed data from BigQuery tables directly into these pushes. The agent analyzes your cloud datasets and alerts your team of pipeline failures without leaving the Google Cloud ecosystem.

Channel Feed Analysis via MCP Server

The MCP server exposes `list_channel_subscriptions` so your Gemini model ingests entire feed histories at once. The model reads these feeds, cross-references them with Vertex AI databases, and decides whether to run `subscribe_to_channel`. Long-context reasoning in the Google ADK allows your agent to parse months of Pushbullet feed data in a single run. You automate complex logic like running `unsubscribe_from_channel` when a channel's content matches specific alert criteria.

Automated Device Registration

Provisioning ephemeral compute nodes with this MCP server lets your agent use `register_new_device` to add hardware targets to your Pushbullet account. Your Google ADK agent monitors system logs and provisions new notification targets dynamically. When a node goes offline, the agent cleans up your account by calling `remove_device` and `remove_push_record`. This ensures your hardware list remains pristine without manual intervention.

Setup guide

Set up Pushbullet MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Pushbullet tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Pushbullet_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Pushbullet tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Pushbullet. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Pushbullet now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Pushbullet MCP in Google ADK

Use McpToolset with StreamableHttpServerParameters pointing to your Vinkius endpoint to expose `send_push_notification` to Gemini. Pass this toolset into your LlmAgent constructor to start routing alerts.

Yes, your agent calls `list_channel_subscriptions` to pull feed data directly into Gemini's context window. You also use `subscribe_to_channel` to programmatically join new channels based on BigQuery data.

The ADK passes your Vinkius endpoint token securely to run `test_pushbullet_auth` at startup. This validates your credentials before the agent attempts to execute `list_connected_devices`.

Yes, you use the optional tool_names filter in McpToolset to limit access. This lets you expose `send_push_notification` while blocking dangerous tools like `remove_device`.

Your device IDs and push history are protected by Google Cloud's enterprise security layers and Vinkius's zero-trust sandbox. The ADK only pulls payloads via `list_recent_pushes` when your agent explicitly requests them.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript