How to Use the Modelbit (ML Model Deployments) MCP in Google ADK

Q: Can I filter which Modelbit models are exposed to my agent?

Yes. Use the toolnames parameter in your McpToolset configuration to explicitly whitelist or blacklist specific endpoints, keeping your agent focused.

Q: Is my sensitive machine learning model input data secure?

Yes. All prediction inputs and model outputs sent through getinference are encrypted in transit. Vinkius runs the MCP connection in a zero-trust, ephemeral sandbox that destroys the runtime state immediately after execution.

Trigger Modelbit (ML Model Deployments) models using Google ADK to process BigQuery data with Gemini models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Modelbit (ML Model Deployments) MCP to Google ADK

Create your Vinkius account to connect Modelbit (ML Model Deployments) 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 Modelbit (ML Model Deployments) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Modelbit model inferences within Google ADK

The `get_inference` tool allows your Gemini-powered agents to execute remote machine learning models directly during a reasoning loop. Your agent pulls raw data from BigQuery, formats it, and sends it to your deployed model. This workflow connects enterprise data pipelines directly to real-time predictions. The agent handles the data transformation, passes it to the tool, and uses the output to make decisions.

Long-context reasoning with production model endpoints

By combining Gemini's million-token context window with this MCP Server, your agent can analyze massive datasets before calling `get_inference`. The agent identifies trends across thousands of documents, extracts the relevant features, and executes the prediction tool. This setup prevents context loss during complex analytical tasks. The agent holds the historical context in memory while using the model endpoint for precise numerical calculations.

Granular tool control for Google Cloud agents

You restrict which models your agent can access by using the optional tool_names filter during initialization. Our configuration ensures the agent only exposes `get_inference` when it is actively required for the current task. This restriction keeps your agent's action space small and focused. It prevents the model from invoking the wrong endpoints. That's it.

Setup guide

Set up Modelbit (ML Model Deployments) 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 Modelbit (ML Model Deployments) 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="Modelbit (ML Model Deployments)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Modelbit (ML Model Deployments) 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 Modelbit. 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 Modelbit (ML Model Deployments) 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 Modelbit (ML Model Deployments) MCP in Google ADK

Instantiate the McpToolset with your Vinkius HTTP transport URL. Pass this toolset instance inside the tools list of your LlmAgent constructor to expose the model endpoints.

Yes. The setup supports both Stdio and HTTP transports, allowing you to connect to the external MCP Server whether you are running a local terminal agent or a cloud-hosted service.

The framework uses the schema exposed by the MCP interface to map input variables. Gemini reads this schema and outputs matching JSON parameters to call the model.

Yes. Use the tool_names parameter in your McpToolset configuration to explicitly whitelist or blacklist specific endpoints, keeping your agent focused.

Yes. All prediction inputs and model outputs sent through `get_inference` are encrypted in transit. Vinkius runs the MCP connection in a zero-trust, ephemeral sandbox that destroys the runtime state immediately after execution.

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