How to Use the Baseten MCP in Google ADK

Q: How do I integrate the Baseten MCP Server with Google ADK?

Run pip install google-adk and initialize an McpToolset using your HTTP endpoint URL. Pass that toolset directly to your LlmAgent constructor.

Q: Can Google ADK filter which Baseten tools are available?

Yes, you can restrict the exposed tools using the optional toolnames filter. This lets you give an agent access to listmodels while blocking predict.

Give Google ADK agents the ability to run Baseten model predictions and inspect active deployments directly from your enterprise cloud.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Baseten MCP to Google ADK

Create your Vinkius account to connect Baseten 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 Baseten with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Baseten Predictions from Google ADK

Running the `predict` tool lets your Gemini agent construct explicit tensor shapes and trigger serverless inference runs on Baseten. Gemini handles massive context windows, so you can dump enormous datasets from BigQuery straight into your external models. Enterprise agents need reliable execution across different cloud environments. This MCP Server bridges that gap, letting your Google Cloud architecture talk to your specialized external deployments without writing custom glue code.

Track Models and Deployments

Using `get_model` and `list_models`, your agent reads exactly which managed models are available in your workspace. It then uses `get_deployment` to pull the explicit details of running instances before routing any traffic. Connecting the endpoints requires adding an `McpToolset` to your `LlmAgent` configuration. You maintain total control over which specific tools the agent sees by applying a tool names filter during setup.

Verify Environment Secrets

Calling the `list_secrets` tool lets your agent audit your workspace configuration by listing securely managed secrets without exposing their values. It confirms the environment is ready for inference runs. Long-context reasoning means your agent can analyze the entire list of active inference bounds via `list_deployments` and compare them against historical logs. That creates a highly autonomous MCP system for monitoring your infrastructure.

Setup guide

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

Run `pip install google-adk` and initialize an `McpToolset` using your HTTP endpoint URL. Pass that toolset directly to your `LlmAgent` constructor.

Yes, you can restrict the exposed tools using the optional `tool_names` filter. This lets you give an agent access to `list_models` while blocking `predict`.

The agent formulates dictionaries or tensor shapes that strictly match your deployed instance. It then calls the prediction endpoint to run serverless inference.

Your agent can check active inference bounds, specific model versions, and running instance details. It pulls this data dynamically to inform routing decisions.

Yes, your inference payloads and model configurations remain entirely private. The connection routes through an ephemeral V8 Isolate Sandbox on Vinkius, meaning your enterprise data is processed securely and destroyed immediately after the request completes.

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