How to Use the Kevel MCP in Google ADK

Q: Is it possible to restrict the agent to specific sites or zones?

You can pass a filtered toolnames array to McpToolset during initialization. This restricts your agent to tools like listzones while hiding advertiser-level tools.

Connect Google ADK agents to the Kevel MCP Server to analyze live ad placements and campaign metrics within your cloud data warehouse.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kevel MCP to Google ADK

Create your Vinkius account to connect Kevel 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 Kevel with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze ad server structures inside Google ADK

The Kevel MCP Server uses `list_sites` and `list_zones` to let your Gemini-powered agents query your ad layout directly. The agent invokes these queries to map your digital properties, feeding that structure straight into your enterprise data pipelines. This setup lets you cross-reference live site structures with your BigQuery datasets. Your agent handles the heavy lifting of pulling zone configurations without manual exports.

Audit flight delivery across channels

This toolset uses `list_flights` and `list_channels` to give your Google ADK agent the ability to check active delivery parameters. By calling these tools, the agent identifies which distribution paths are currently active. You can run these checks over long conversations. Because Gemini handles massive context windows, your agent can compare hundreds of flights returned by `list_flights` against your historical performance logs.

Track advertiser assets and creatives

Your agent pulls your entire creative library by calling `list_creatives` and `list_ads`. It matches these assets against specific advertiser accounts retrieved via `list_advertisers` to ensure brand safety. You get direct verification of what is live. The agent inspects the properties of each creative using `get_campaign` to make sure the right assets are serving to the right audiences.

Setup guide

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

Yes, you configure the connection using StreamableHttpServerParameters pointing to your Vinkius endpoint. This exposes all eleven Kevel tools directly to your Google ADK agent.

Gemini's long-context window easily processes large JSON payloads returned by `list_creatives`. The Google ADK agent parses the entire list of assets in a single turn without running out of memory.

Yes, you can build an agent that queries BigQuery for performance metrics and then uses this MCP Server to pull campaign details via `get_campaign`. This lets the agent match offline revenue data with live ad server settings.

You can pass a filtered tool_names array to McpToolset during initialization. This restricts your agent to tools like `list_zones` while hiding advertiser-level tools.

Vinkius executes the Kevel connection inside ephemeral, zero-trust sandboxes. Your advertiser IDs and creative metadata are fetched on demand and are never stored or logged on the Vinkius platform.

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