How to Use the NVIDIA API Catalog MCP in Google ADK

Q: How do I connect the NVIDIA API Catalog to a Google ADK agent?

Run pip install google-adk and initialize the MCP toolset with your Vinkius HTTP transport URL. Pass this toolset into your LlmAgent constructor inside the tools list to expose all eight tools.

Q: Can Google ADK filter tools from the NVIDIA API Catalog?

Yes, you can use the optional toolnames filter in the toolset configuration. This allows you to restrict your agent to specific tools like nvidiachatcompletion while hiding administration tools.

Q: How does the agent handle custom fine-tuned models?

The agent calls nvidialistloraadapters to discover active fine-tuned overrides. It can then target these specialized adapters during subsequent chat or vision inference calls.

Q: What happens to the BigQuery data processed by this MCP Server?

BigQuery rows converted via nvidiagenerateembeddings are processed in-memory inside an ephemeral V8 sandbox. Vinkius never caches your embeddings vectors or database payloads, ensuring your enterprise data remains confined to your Google Cloud and NVIDIA endpoints.

Feed BigQuery data directly to Llama3 and Nemotron models using Google ADK and native cloud tracking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA API Catalog MCP to Google ADK

Create your Vinkius account to connect NVIDIA API Catalog 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 API Catalog with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Power Google ADK agents with NVIDIA foundation models

Bring specialized architectures into your Gemini-driven pipelines without manual API mapping. This MCP Server exposes `nvidia_list_foundation_models` so your Google ADK agent instantly identifies and targets active Nemotron or Llama3 endpoints. Your agent calls `nvidia_chat_completion` to process complex reasoning tasks. It combines Gemini's massive context window with NVIDIA's rapid inference speeds, keeping your pipeline fast.

Direct vector generation for BigQuery pipelines

Turn raw enterprise database rows into searchable vectors on the fly. Your agent triggers `nvidia_generate_embeddings` to process BigQuery rows and write them back into Google Cloud storage. To keep your CFO happy, make the agent call `nvidia_check_token_quota` before running heavy batch vectorization tasks. This blocks unexpected billing spikes during automated ETL runs.

Process visual data and summarize text natively

Handle complex document analysis directly in your Google Cloud ecosystem. The agent calls `nvidia_summarize_content` to condense large reports before saving them to Vertex AI vector search. For visual tasks, your agent uses `nvidia_vision_inference` to analyze graphics and generate structured metadata. This allows Gemini agents to process images alongside enterprise data via the MCP standard.

Setup guide

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

Run `pip install google-adk` and initialize the MCP toolset with your Vinkius HTTP transport URL. Pass this toolset into your `LlmAgent` constructor inside the `tools` list to expose all eight tools.

Yes, you can use the optional `tool_names` filter in the toolset configuration. This allows you to restrict your agent to specific tools like `nvidia_chat_completion` while hiding administration tools.

Yes, you can pass large context blocks retrieved by Gemini to `nvidia_summarize_content` to prepare them for downstream processing. This combines Google's massive context handling with NVIDIA's rapid inference capabilities.

The agent calls `nvidia_list_lora_adapters` to discover active fine-tuned overrides. It can then target these specialized adapters during subsequent chat or vision inference calls.

BigQuery rows converted via `nvidia_generate_embeddings` are processed in-memory inside an ephemeral V8 sandbox. Vinkius never caches your embeddings vectors or database payloads, ensuring your enterprise data remains confined to your Google Cloud and NVIDIA endpoints.

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