How to Use the Huawei Push Kit / 华为推送服务 MCP in Google ADK

Q: How do I integrate the Huawei Push Kit / 华为推送服务 with Google ADK?

You wrap the server URL in a McpToolset and pass it to your LlmAgent as a tool. Google ADK handles the discovery. You can also filter the tool list if you only want your agent to access certain functions, like sending but not subscribing.

Connect Google ADK agents to Huawei's push service. Trigger notifications from BigQuery events or other Google Cloud services.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Huawei Push Kit / 华为推送服务 MCP to Google ADK

Create your Vinkius account to connect Huawei Push Kit / 华为推送服务 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 Huawei Push Kit / 华为推送服务 with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Pushes from Google Cloud

The `push_to_token` and `push_to_topic` tools let your Gemini-powered agent send notifications directly. You can build agents that watch a BigQuery table and trigger a `push_to_token` call when a new row is added, connecting your data warehouse to your users' phones. Because Google ADK agents have a massive context window, they can analyze large amounts of data to decide which notification to send. Feed your agent user activity logs, and it can choose the right message and use `push_to_topic` to send a perfectly timed marketing alert.

Enterprise-Scale Topic Management

Manage your HMS topic subscriptions right from your Google ADK agent. Use the `subscribe_to_topic` and `unsubscribe_from_topic` tools to automate user preferences. This lets you sync notification settings with your central user database in Cloud SQL or Spanner. This MCP server makes it simple. The agent just calls the tool; it doesn't need to know about OAuth tokens or Huawei's specific API syntax. You can even build a maintenance agent that uses `list_topic_subscriptions` to audit your system for stale subscriptions.

Your Gemini Agent on this MCP Server

Go beyond simple topic pushes with `push_to_condition`. Your agent can construct complex boolean logic to target specific cohorts of users, offloading the filtering work to Huawei's backend instead of running it on your own infrastructure. This is especially powerful when combined with Vertex AI. Train a model to identify user segments, then have your Google ADK agent translate those segments into a condition string for the `push_to_condition` tool. It's a direct line from your data models to your users' devices.

Setup guide

Set up Huawei Push Kit / 华为推送服务 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 Huawei Push Kit / 华为推送服务 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="Huawei Push Kit / 华为推送服务_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Huawei Push Kit / 华为推送服务 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 Huawei Push Kit / 华为推送服务. 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 Huawei Push Kit / 华为推送服务 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 Huawei Push Kit / 华为推送服务 MCP in Google ADK

You wrap the server URL in a `McpToolset` and pass it to your `LlmAgent` as a tool. Google ADK handles the discovery. You can also filter the tool list if you only want your agent to access certain functions, like sending but not subscribing.

Absolutely, that's a core use case. Your Google ADK agent can query BigQuery, get a list of device tokens, and then loop through them using the `push_to_token` tool from this MCP server.

It's the native fit with the Google Cloud ecosystem. Your agent can reason over data in BigQuery, be triggered by Pub/Sub, and use tools from this MCP Server to act on that data by notifying users on HMS devices.

Yes. You can feed the agent a large report or a long list of user data. It can then use that context to make smarter decisions about who to notify using the `push_to_topic` or `push_to_condition` tools.

The server only processes the device tokens and topic names your agent provides for a specific call. Access is controlled by a single endpoint token. You can also lock down which services can call this MCP endpoint using Google Cloud IAM and firewall rules.

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