How to Use the Google Cloud Functions MCP in Google ADK

Build enterprise agents acting on BigQuery with Google ADK and Google Cloud Functions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Google Cloud Functions MCP to Google ADK

Create your Vinkius account to connect Google Cloud Functions to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Google Cloud Functions with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Execute remote, heavy processing

When your agent needs to run complex logic against structured data sources, the `gcf_invoke_function` tool gets it done. Your AI client invokes this MCP to trigger a secure serverless compute task defined in Google Cloud Functions. This is ideal for executing ETL (Extract, Transform, Load) steps or performing specialized calculations that need dedicated backend resources.

Connect agents to enterprise logic

The ADK lets you build agent systems that don't just chat; they act on your existing data in BigQuery. You can define a function that acts as the bridge between Gemini models and your company’s core business processes. This capability means your agents move beyond prototypes and interact directly with production-grade, enterprise tooling.

Manage complex multi-step tasks

Your agent can orchestrate a sequence of operations using this MCP. You pass the initial context, and then the function executes multiple steps—maybe querying BigQuery, running analysis, and finally calling out to an external service. This flow ensures that the entire automated process is contained within traceable, defined compute boundaries.

Setup guide

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

The ADK framework uses this MCP to expose external computation as a native tool. You simply pass the MCPServer object into your LlmAgent, and it handles connecting to Google Cloud Functions for execution.

Use it when you need Gemini models to perform actions that require specialized backend work. For example, automatically classifying a BigQuery record based on complex business rules.

Yes. Because every call is mediated by the MCP inside Vinkius's sandbox, you get a cryptographically signed audit trail for every function execution. Nothing happens in the dark.

Yes. The system is built to handle enterprise loads. While the functions themselves must be stateless, they are designed to process inputs derived from your massive BigQuery datasets effectively.

This MCP primarily touches structured JSON data representing function parameters and results. It operates on the logical output of your agents, ensuring data remains typed and traceable throughout the call chain.

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