How to Use the Adikteev MCP in Google ADK

Q: Can Google ADK restrict which Adikteev functions the agent calls?

Yes, you can limit access using the toolnames filter. If you only want Gemini to read data, you expose the reporting tool and block it from creating new segments.

Connect the Adikteev server to Google ADK and let Gemini analyze your app retargeting campaigns alongside your 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 Adikteev MCP to Google ADK

Create your Vinkius account to connect Adikteev 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 Adikteev with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Adikteev metrics to BigQuery

Giving your Gemini agent the `get_reporting` tool bridges the gap between your Google Cloud data and your app marketing. The agent pulls campaign performance metrics from Adikteev and cross-references them against your internal revenue tables. Gemini's massive context window means it can process months of raw ad spend data at once. It reads the output, spots trends in user acquisition costs, and writes a summary directly to your Vertex AI workspace.

Predict and prevent user drop-off

By calling `get_churn_scores`, your Google ADK agent identifies which specific cohorts are losing interest in your mobile app. It processes these risk levels and compares them against usage logs stored in your cloud infrastructure. The agent doesn't just report the problem. It immediately runs `create_segment` to build a custom retargeting audience for those at-risk users, allowing your ad creatives to win them back automatically.

Audit audience overlap at scale

Your agent uses `list_segments` to pull down every active audience currently running in your account. It maps out exactly who you are targeting across different campaigns to ensure you aren't wasting budget on overlapping ad sets. If the agent needs to verify which regional account it is looking at, it triggers `list_companies` to grab the correct ID. You can restrict the agent to only use these read-only tools by setting the tool_names filter in your Google setup.

Setup guide

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

Pass your Vinkius endpoint URL into StreamableHttpServerParameters. Then wrap that in a McpToolset and hand it to your LlmAgent tools array. Gemini will automatically map the retargeting functions.

Yes, you can limit access using the tool_names filter. If you only want Gemini to read data, you expose the reporting tool and block it from creating new segments.

Yes. You can pull massive datasets using the reporting tools and feed them straight into a 1M+ token context. The model analyzes the entire campaign history in one pass without dropping details.

Most API actions require an account identifier to route the request properly. The agent calls the company listing tool in the background to grab this required parameter before trying to fetch your ad stats.

Every connection runs through a zero-trust architecture. When your Gemini agent retrieves lists of audience segments or churn predictions, the execution happens in an isolated environment that vanishes immediately after the response is sent.

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