How to Use the DeepInfra (Serverless LLM Inference) MCP in Google ADK

Bring DeepInfra LLMs into your Google ADK enterprise agents to extend reasoning capabilities.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepInfra (Serverless LLM Inference) MCP to Google ADK

Create your Vinkius account to connect DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect DeepInfra to Google ADK agents

Map the `create_chat_completion` tool into your existing toolset configuration. Your agent gains the ability to reach out to high-performance models outside the standard Vertex ecosystem. It works as a native extension of your agent framework. You define the tool names and the agent manages the rest.

Process visual data with `generate_image`

Inject image generation into your agent's output stream using a simple call. This tool creates the visual assets your business process requires on-demand. Your agent controls the prompt and receives the image data directly. It saves you from building custom integrations for image rendering.

Execute complex `run_native_inference` tasks

Utilize models that perform OCR or specialized data extraction directly from your agent. This is perfect for scraping unstructured data from your cloud storage. The tool returns the processed result to your agent's workspace. You can then pipe that data straight into BigQuery for analysis.

Setup guide

Set up DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) 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="DeepInfra (Serverless LLM Inference)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to DeepInfra (Serverless LLM Inference) 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 DeepInfra. 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 DeepInfra (Serverless LLM Inference) 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 DeepInfra (Serverless LLM Inference) MCP in Google ADK

You use the McpToolset class provided by the framework. Just point it at your Vinkius server URL to grant your agent access to all four tools.

Yes, you can use it alongside your existing Gemini setups. It acts as an auxiliary inference engine when you need to switch models for specific tasks.

Absolutely, you can restrict which tools are available to your agent. Use the tool_names filter to ensure your agent only accesses what it actually needs.

The serverless backend scales automatically. You don't need to worry about provisioning or scaling infrastructure for your agents.

Data sent through the server is ephemeral. We clear the memory buffers after each inference cycle, ensuring no residual data remains.

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