Can I generate images from text?

Yes! Use the `generate_image` tool with Stable Diffusion models. Provide a descriptive prompt and optionally specify size (e.g., '1024x1024').

Can I ask questions about an image?

Yes! Use `visual_question_answering` with a public image URL and your question. The AI will analyze and respond with details about the image.

Does it work with scanned documents?

Yes! Use `document_qa` to extract information from scanned documents, forms, receipts, and other image-based documents.

What image sizes can I generate?

Stable Diffusion models support various sizes including 512x512, 768x768, and 1024x1024. Higher resolutions produce more detailed images but take longer to generate.

NVIDIA Vision MCP Server for Google ADK 9 tools — connect in under 2 minutes

Name: NVIDIA Vision
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 9 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add NVIDIA Vision as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="nvidia_vision_agent",
    instruction=(
        "You help users interact with NVIDIA Vision "
        "using 9 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About NVIDIA Vision MCP Server

Connect NVIDIA Vision to any AI agent and unlock powerful image understanding and generation — create images with Stable Diffusion, analyze visuals with Kosmos-2, answer questions about images, and perform object detection through natural conversation.

Google ADK natively supports NVIDIA Vision as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 9 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Generate Images — Create images from text prompts using Stable Diffusion models
Visual Q&A — Ask questions about any image and get detailed answers
Image Captioning — Generate detailed descriptions of image contents
Object Detection — Identify and list all objects visible in an image
Document Understanding — Extract information from scanned documents and forms
Visual Grounding — Locate specific objects or phrases within images
Style Transfer — Apply artistic styles to existing images
Image Segmentation — Segment images into distinct object regions

The NVIDIA Vision MCP Server exposes 9 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect NVIDIA Vision to Google ADK via MCP

Follow these steps to integrate the NVIDIA Vision MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 9 tools from NVIDIA Vision via MCP

Why Use Google ADK with the NVIDIA Vision MCP Server

Google ADK provides unique advantages when paired with NVIDIA Vision through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with NVIDIA Vision

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine NVIDIA Vision tools with BigQuery, Vertex AI, and Cloud Functions

NVIDIA Vision + Google ADK Use Cases

Practical scenarios where Google ADK combined with the NVIDIA Vision MCP Server delivers measurable value.

Enterprise data agents: ADK agents query NVIDIA Vision and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine NVIDIA Vision tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query NVIDIA Vision regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including NVIDIA Vision

NVIDIA Vision MCP Tools for Google ADK (9)

These 9 tools become available when you connect NVIDIA Vision to Google ADK via MCP:

detect_objects

Detect and list all objects in an image

document_qa

Works with scanned documents, forms, receipts. Ask questions about a document image (OCR + understanding)

generate_image

Model options: "stabilityai/stable-diffusion-3-medium", "stabilityai/stable-diffusion-xl-base-1.0". Size format: "1024x1024". Generate an image from a text prompt using Stable Diffusion

image_captioning

Generate a detailed caption for an image

image_segmentation

Segment and identify all objects in an image

list_vision_models

List available vision models on NVIDIA API Catalog

style_transfer

Apply an artistic style to an image

visual_grounding

Locate a specific object or phrase in an image

visual_question_answering

Provide a public image URL. Ask a question about an image

Example Prompts for NVIDIA Vision in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with NVIDIA Vision immediately.

"Generate an image of a futuristic city at sunset."

"What objects do you see in this image: https://example.com/photo.jpg"

"Describe this image in detail: https://example.com/document.png"

Troubleshooting NVIDIA Vision MCP Server with Google ADK

Common issues when connecting NVIDIA Vision to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

NVIDIA Vision + Google ADK FAQ

Common questions about integrating NVIDIA Vision MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.