How to Use the Autobidder MCP in Google ADK

Q: How do I pass Autobidder tools to a Google ADK agent?

You initialize McpToolset using the Streamable HTTP transport pointing to your Vinkius URL. Then, pass this toolset directly into your LlmAgent constructor to expose the bidding functions to Gemini.

Q: Can I restrict the Google ADK to read-only Autobidder tools?

Yes, you can use the toolnames filter when setting up your toolset. This lets you expose listrequests and getbid while blocking access to destructive or financial actions like createrequest.

Q: Is my Autobidder bidding profile safe when using Google ADK?

All credentials and profile details fetched via getprofile are transmitted over TLS directly to your execution environment. Vinkius operates a zero-trust network topology, ensuring your bidding strategies and financial limits are never exposed to external logs.

Feed real-time ad performance data directly into your Gemini enterprise agents with Autobidder and Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Autobidder MCP to Google ADK

Create your Vinkius account to connect Autobidder 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 Autobidder with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scale enterprise ad bidding with Google ADK

Connect Gemini's million-token context window directly to your ad platforms using this MCP Server. Your enterprise agents can pull massive arrays of campaign data using `list_projects` and feed them into Vertex AI for long-context reasoning. The Google ADK allows your agent to cross-reference these active projects against historical performance tables stored in BigQuery, making your bidding decisions incredibly data-driven.

Analyze historical outcomes and optimize bids

Let your Gemini agent fetch deep campaign histories using `list_outcomes` and `get_outcome`. The agent parses these results to determine which bidding strategies yielded the highest return on ad spend. By combining Google ADK's native cloud logging with the `get_bid` tool, your engineering team can audit every single bid adjustment made via the MCP.

Initiate ad bid requests programmatically

Automate your media buying pipeline by letting your agent execute `create_request` based on real-time inventory signals. The agent verifies client credentials and budget caps first by calling `get_profile` and `get_request`. This integration exposes the Autobidder tools as native functions within your `LlmAgent` using our MCP endpoint, allowing Gemini to execute complex bidding chains without manual intervention.

Setup guide

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

You initialize `McpToolset` using the Streamable HTTP transport pointing to your Vinkius URL. Then, pass this toolset directly into your `LlmAgent` constructor to expose the bidding functions to Gemini.

Yes, this setup is fully compatible with serverless environments. The ADK handles the HTTP transport lifecycle, making it easy to trigger `check_autobidder_status` inside a Cloud Run container.

Gemini's large context window easily processes long lists of bids returned by `list_bids`. The ADK passes the raw JSON output from the MCP Server directly into the model's context without truncation.

Yes, you can use the `tool_names` filter when setting up your toolset. This lets you expose `list_requests` and `get_bid` while blocking access to destructive or financial actions like `create_request`.

All credentials and profile details fetched via `get_profile` are transmitted over TLS directly to your execution environment. Vinkius operates a zero-trust network topology, ensuring your bidding strategies and financial limits are never exposed to external logs.

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