How to Use the AdRoll MCP in Google ADK

Q: How do I connect the AdRoll MCP server to my Google ADK agent?

You instantiate an McpToolset with your Vinkius server URL. Then you pass that toolset into your LlmAgent's tools parameter. The ADK handles the rest, making tools like getcampaign available to your Gemini model.

Q: Does the AdRoll MCP server work with Gemini's long context?

Yes. Your Gemini agent can use tools like listcampaigns and listads to gather a lot of information from AdRoll. It can then hold all that context in memory to make more informed decisions or generate more detailed reports.

Q: How do I limit which AdRoll tools my Google ADK agent can use?

When you create the McpToolset, you can pass an optional toolnames filter. This lets you expose only a specific subset of the AdRoll tools, like just getreport, to a particular agent for security or focus.

Connect Google ADK agents to your AdRoll account. Analyze campaign data with Gemini and BigQuery's scale.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdRoll MCP to Google ADK

Create your Vinkius account to connect AdRoll 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 AdRoll with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull AdRoll Data into BigQuery

This MCP Server's `get_report` tool lets your agent fetch AdRoll performance metrics. Because you're using Google ADK, you can build agents that pipe this data directly into a BigQuery table for large-scale analysis. No more manual CSV exports. A Gemini-powered agent can handle the long context needed to analyze complex reports. It can use `list_campaigns` and `list_adgroups` to gather context, then call `get_report` with fine-tuned criteria, and finally summarize its findings based on the results.

Enterprise Agents on Google Cloud

The `list_advertisables` and `list_campaigns` tools give your agent the ability to navigate your AdRoll account structure. You're not just running one-off queries; you're building stateful agents that understand your marketing setup. With Google ADK, these agents live natively in the Google Cloud ecosystem. This means they can be triggered by Cloud Functions, log to Cloud Logging, and integrate with Vertex AI pipelines, using the AdRoll MCP as their connection to your ad platform.

Analyze Segments and Ads at Scale

Use the `list_segments` tool to have your agent pull all your defined audience segments from AdRoll. This is the first step in building an automated system that correlates audience data with performance metrics from `get_report`. You can also have an agent inventory all your creative assets with `list_ads`. Thanks to Gemini's large context window, the agent can hold information on hundreds of ads and campaigns simultaneously while it reasons about performance trends.

Setup guide

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

You instantiate an `McpToolset` with your Vinkius server URL. Then you pass that toolset into your `LlmAgent`'s `tools` parameter. The ADK handles the rest, making tools like `get_campaign` available to your Gemini model.

Absolutely. That's the main point of using Google ADK. An agent can pull a report with `get_report`, process it, and write the results to BigQuery or trigger a Vertex AI job.

Yes. Your Gemini agent can use tools like `list_campaigns` and `list_ads` to gather a lot of information from AdRoll. It can then hold all that context in memory to make more informed decisions or generate more detailed reports.

When you create the `McpToolset`, you can pass an optional `tool_names` filter. This lets you expose only a specific subset of the AdRoll tools, like just `get_report`, to a particular agent for security or focus.

Your AdRoll campaign and performance data is processed within an ephemeral, zero-trust environment on Vinkius servers. Your agent's requests are authenticated via a single token, and the data passes through our sandboxed environment without being logged or stored.

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