How to Use the NVIDIA NIM MCP in Google ADK

Q: How do I check local GPU memory limits?

The agent calls nimgetgpustatus to inspect physical VRAM limits. This provides the exact topological mapping of your hardware resources.

Manage local hardware limits and model deployments directly from your Google ADK enterprise pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA NIM MCP to Google ADK

Create your Vinkius account to connect NVIDIA NIM 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 NVIDIA NIM with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query active hardware metrics inside Google ADK

Telemetry is pulled via `nim_get_metrics` to extract raw Prometheus metrics directly from your running containers. Your agent analyzes this performance data alongside BigQuery tables to correlate database load with GPU performance.\n\nBy combining these sources, your agent can spot bottlenecks before they cause downtime. It pulls raw metrics directly, skipping slow manual monitoring dashboards.

Verify deployment readiness with this MCP Server

This MCP Server uses `nim_check_health_ready` to verify that the GPU inference layers have successfully loaded your model weights. The agent checks this status before routing production traffic from Google ADK endpoints.\n\nIf a container is still warming up, the agent waits. It uses `nim_check_health_live` to confirm the host orchestrator is online, preventing dropped requests during deployments.

Track container logs and engine metadata

We call `nim_get_container_logs` to retrieve stdout streams from the active container orchestrator. Your agent parses these logs to debug failed inference calls or driver mismatches.\n\nFor configuration audits, `nim_get_metadata` pulls the foundational engine parameters. The agent matches these engine bounds against your Google Cloud infrastructure specs to ensure compatibility.

Setup guide

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

You register the server parameters with your Google ADK toolset. The Gemini models then call tools like `nim_list_models` to inspect active inference backends.

Yes, you can pass a tool names filter to the toolset configuration. This lets you restrict access to destructive operations like `nim_scale_replicas`.

Yes, your Google ADK agents can process large volumes of container logs using Gemini's long context window. The agent calls `nim_get_container_logs` to ingest and analyze thousands of log lines at once.

The agent calls `nim_get_gpu_status` to inspect physical VRAM limits. This provides the exact topological mapping of your hardware resources.

Vinkius routes all tool calls through an ephemeral, zero-trust sandbox. Your container logs and hardware metrics are processed in memory and never stored on persistent disks.

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