How to Use the MOBIDI MCP in Google ADK

Q: How do I initialize MOBIDI tools in google-adk?

Use the McpToolset class with the server's HTTP parameters to register the tools. Pass this toolset directly to your LlmAgent to let Gemini call the campaign management functions.

Q: Can google-adk restrict which MOBIDI tools are exposed?

Yes, you can pass a toolnames filter to the toolset initialization to restrict access. This stops the agent from running destructive actions like deleterecord if you only want reporting.

Q: Does google-adk support real-time bidding updates on MOBIDI?

Yes, the agent can use updaterecord to adjust bid values instantly based on incoming performance data. This allows closed-loop optimization directly from your Google Cloud environment.

Q: How do I check if the connection is active?

Your agent can call checkmobidistatus to check the MCP link health. This ensures the integration is live before running complex campaign operations.

Connect Gemini to MOBIDI through Google ADK to run ad campaign operations directly from BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MOBIDI MCP to Google ADK

Create your Vinkius account to connect MOBIDI 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 MOBIDI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync BigQuery data with MOBIDI using Google ADK

Your Gemini agent can query mobile attribution metrics using `list_records` to find mismatched budgets. It pulls targeting data from your warehouse and updates live campaigns on the fly. This setup bridges your BigQuery data with active MOBIDI ad networks. You don't need intermediate scripts to push changes when `update_record` handles it directly.

Long-context campaign analysis via MCP Server

Feed massive raw performance logs into Gemini's long-context window and let the agent call `execute_report` to cross-reference the data. The model analyzes thousands of lines of campaign history to find hidden spend leaks. By using this MCP Server, your Google ADK agent can compare historical trends with current active states retrieved by `get_report`. It gives your team deep insights without manual spreadsheet work.

Manage mobile ad entities at scale

Keep your Google ADK campaign structures clean by letting the agent inspect your MOBIDI setup with `list_entity_types`. If a tracking structure is broken, the agent can trigger `delete_record` to prune dead ad sets. This maintains your MOBIDI account hygiene automatically within the Google Cloud ecosystem. The Google ADK handles the raw execution, so your agent can focus on optimizing mobile acquisition targets.

Setup guide

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

Use the `McpToolset` class with the server's HTTP parameters to register the tools. Pass this toolset directly to your `LlmAgent` to let Gemini call the campaign management functions.

Yes, you can pass a `tool_names` filter to the toolset initialization to restrict access. This stops the agent from running destructive actions like `delete_record` if you only want reporting.

Yes, the agent can use `update_record` to adjust bid values instantly based on incoming performance data. This allows closed-loop optimization directly from your Google Cloud environment.

Your agent can call `check_mobidi_status` to check the MCP link health. This ensures the integration is live before running complex campaign operations.

Your MOBIDI tracking URLs and active campaign lists are kept strictly within our sandboxed V8 runtime. We use temporary single-use session tokens to authenticate, meaning your raw keys never persist in the Google ADK environment.

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