How to Use the Novu MCP in Google ADK

Q: Can my Gemini agent create new Novu notification templates using Google ADK?

Yes, your agent can call createlayout and createworkflow using the tools provided by this MCP Server. The Google ADK passes the structured layouts generated by Gemini directly to your account.

Q: How do I restrict which Novu tools my Google ADK agent can access?

You can use the toolnames filter in the Google ADK setup to restrict access. For example, you can expose only triggerevent and block administrative tools like deletesubscriber for safety.

Q: Can the agent check if a user is subscribed to a specific notification feed?

Yes, the agent runs checktopicsubscriber to verify subscription status. It will return a direct boolean response, allowing the agent to decide whether to trigger an alert.

Q: How does the MCP Server handle subscriber API credentials and tokens?

Any authentication tokens passed through upsertsubscribercredentials are encrypted in transit using standard TLS. The Vinkius sandbox executes the request in a zero-trust environment, ensuring your API keys are never cached or exposed to external networks.

Connect Gemini's long-context reasoning to your Novu notification delivery channels using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Novu MCP to Google ADK

Create your Vinkius account to connect Novu 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 Novu with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery-driven Novu dispatch via Google ADK

Feed massive datasets from BigQuery directly into Gemini's context window and let your Google ADK agent handle the outreach. The model analyzes user behavior over millions of tokens, identifies inactive accounts, and immediately fires off personalized alerts using `trigger_event` or `trigger_broadcast` via Novu. This eliminates the need for complex cron jobs and middleware. Your Google ADK agent reads the database, writes the notification copy, and executes the delivery via this MCP Server in a single, continuous runtime loop.

Enterprise topic routing and subscriber sync

Manage large-scale communication channels by exposing Novu's topic tools to your Gemini agent via the MCP Server. Using `create_topic` and `create_topic_subscriptions`, the Google ADK agent organizes thousands of users into targeted segments based on real-time data from Vertex AI. The Google ADK agent checks subscription status with `check_topic_subscriber` before blasting updates. If a subscriber needs to be removed, the agent calls `delete_topic_subscriptions` to keep your Novu lists clean and reduce unnecessary message volume.

Dynamic environment and integration auditing

Keep your production environments secure and functional by letting your Google ADK agent audit your Novu setups. The agent calls `list_integrations` and `get_environment_variable_usage` to verify that your active delivery channels match your Google Cloud deployment configurations. If a credential needs an update, the agent uses `update_subscriber_credentials` to rotate Novu access keys safely. This ensures your communication pipelines stay active without manual intervention from your DevOps team.

Setup guide

Set up Novu 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 Novu 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="Novu_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Novu 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 Novu. 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 Novu 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 Novu MCP in Google ADK

The Google ADK uses Gemini's long context to process large batches of subscriber IDs, which it then passes directly to the `trigger_broadcast` tool. This allows your agent to handle massive notification runs without running out of memory.

Yes, your agent can call `create_layout` and `create_workflow` using the tools provided by this MCP Server. The Google ADK passes the structured layouts generated by Gemini directly to your account.

You can use the `tool_names` filter in the Google ADK setup to restrict access. For example, you can expose only `trigger_event` and block administrative tools like `delete_subscriber` for safety.

Yes, the agent runs `check_topic_subscriber` to verify subscription status. It will return a direct boolean response, allowing the agent to decide whether to trigger an alert.

Any authentication tokens passed through `upsert_subscriber_credentials` are encrypted in transit using standard TLS. The Vinkius sandbox executes the request in a zero-trust environment, ensuring your API keys are never cached or exposed to external networks.

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