How to Use the Mav MCP in Google ADK

Q: How does Google ADK handle Mav tool filtering?

You can pass a toolnames list to the McpToolset constructor. This limits which Mav playbooks your agent can access.

Connect Mav to Google ADK to trigger SMS playbooks directly from your Gemini-powered enterprise agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mav MCP to Google ADK

Create your Vinkius account to connect Mav 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 Mav with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Native integration for Google ADK agents

The McpToolset class bridges your Google Cloud infrastructure with Mav. You can now call SMS playbooks as if they were local functions within your agent logic. This works seamlessly with Gemini models holding massive context windows. Your agent can pull lead history from BigQuery and immediately trigger a follow-up via Mav.

Flexible transport for Google ADK

Choose between Stdio or HTTP transports based on where you host your agent. This flexibility allows you to run Mav inside your existing Google Cloud compute environment. Restricting access is simple. Use the tool_names filter to ensure your agent only touches the specific playbooks you want it to run.

Scaling SMS engagement on Google Cloud

Your agents can manage thousands of lead interactions simultaneously. By offloading the communication logic to Mav, your Gemini agent remains performant. You avoid the latency spikes common in custom-built integrations. Everything stays within the Google ecosystem, keeping your operations predictable and fast.

Setup guide

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

Absolutely. You initialize the McpToolset and pass it to your LlmAgent to start triggering SMS playbooks from your Gemini workflows.

You can pass a tool_names list to the McpToolset constructor. This limits which Mav playbooks your agent can access.

It does. Whether you prefer Stdio for local dev or HTTP for cloud deployment, the toolset handles the connection.

Yes. Since your agent can access both, you can write logic that reads lead intent from BigQuery and triggers the right Mav SMS playbook.

Data sent to Mav remains isolated within your project boundary. The Google ADK environment uses standard GCP security, meaning your lead SMS logs never leak into public model training sets.

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