How to Use the Measured MCP in Google ADK

Q: How does the agent identify which channels are currently active?

The agent executes listchannels to get a clean list of all tracked marketing platforms. It can then run getperformancebychannel for each active platform to build a complete picture of your media mix.

Connect Measured incrementality data to your Google ADK pipelines to feed real-time attribution metrics directly into BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Measured MCP to Google ADK

Create your Vinkius account to connect Measured 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 Measured with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise attribution modeling with Google ADK

The `get_performance_by_channel` tool lets your Gemini agent extract granular performance metrics for any marketing channel you track. Instead of exporting CSVs, your Google ADK agent pulls this data directly into your enterprise cloud environment to compare against your internal warehouse. Your agent uses the long-context window of Gemini to analyze months of performance history retrieved via `list_reports`. This allows the agent to spot long-term seasonal trends and cross-reference them with your active campaigns without running out of token space.

Real-time incrementality updates inside your MCP Server

The `get_incrementality_scores` tool provides the raw lift metrics your business needs to justify ad spend. Your Google ADK agent calls this tool to identify which channels are actually driving incremental revenue versus those simply claiming credit. Because this MCP Server runs in a secure sandbox, your enterprise agent can safely query these scores alongside your BigQuery data. The agent runs `get_insights` to generate executive summaries that highlight which platforms are underperforming based on true incrementality.

Automated campaign audits across integrations

The `get_campaign_performance` tool allows your agent to drill down into specific ad campaigns to check their ROAS. Your agent can cross-reference this data by calling `list_integrations` to verify which platforms are feeding active performance metrics. This setup lets you build autonomous auditing pipelines in the Google ADK framework. The agent monitors your active channels via `list_channels` and flags any sudden performance drops directly to your data team.

Setup guide

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

You use the McpToolset class and pass the secure Vinkius HTTP endpoint parameter. Vinkius acts as the proxy, so your Google ADK code only needs a single token to access all your marketing data.

Yes. Gemini's long-context window easily handles the raw JSON data returned by `get_performance_summary` and `list_reports`. The model can analyze complex cross-channel metrics without losing track of previous instructions.

No. Vinkius hosts this MCP Server in a managed, zero-trust cloud environment. Your Google ADK agent connects via Streamable HTTP, meaning you do not have to manage local server processes or runtimes.

The agent executes `list_channels` to get a clean list of all tracked marketing platforms. It can then run `get_performance_by_channel` for each active platform to build a complete picture of your media mix.

All requests transit through an ephemeral V8 Isolate sandbox that enforces zero-trust architecture. Your raw campaign performance and incrementality scores are never persisted on Vinkius servers, keeping your proprietary marketing data isolated within your Google Cloud boundary.

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