How to Use the Hugging Face Vision MCP in Google ADK

Q: Is there a way to restrict which tools my Google ADK agent can access?

Yes, you can use the toolnames filter in McpToolset to limit exposure. For example, you can restrict an agent to only use imageclassification while blocking resource-heavy tools like imagesegmentation.

Equip your Google ADK enterprise agents to process raw images using an MCP Server alongside massive BigQuery datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hugging Face Vision MCP to Google ADK

Create your Vinkius account to connect Hugging Face Vision 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 Hugging Face Vision with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Context-aware image captioning for Google ADK

This Hugging Face Vision MCP server connects the `image_to_text` tool directly to your Gemini-powered pipelines. Your agent takes raw images from cloud storage, generates descriptive captions, and feeds that text into Gemini's 1M-token context window. This approach allows your agent to cross-reference visual descriptions with massive text datasets stored in BigQuery. You get highly detailed visual indexing without writing custom computer vision pipelines from scratch.

Enterprise object tracking and classification

The `object_detection` tool outputs precise bounding boxes, while `image_classification` assigns labels to specific regions of interest. Your Google ADK agent parses these structured outputs to catalog physical assets or monitor inventory levels. Because Vinkius handles the underlying authentication and hosting, your enterprise agents access these tools through a single secure endpoint. This eliminates the need to manage individual API keys across multiple cloud functions.

Image segmentation and generation pipelines

The `image_segmentation` tool splits images into semantic masks, and the `text_to_image` tool generates new visuals from text descriptions. Your agent can run these tools in sequence to modify product mockups based on customer feedback. The entire process is managed via the standard MCP specification, allowing your Google ADK agent to switch models seamlessly. It ensures that your visual generation workflows remain highly modular and easy to maintain.

Setup guide

Set up Hugging Face Vision 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 Hugging Face Vision 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="Hugging Face Vision_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Hugging Face Vision 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 Hugging Face Vision. 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 Hugging Face Vision 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 Hugging Face Vision MCP in Google ADK

Use the McpToolset class with the Vinkius HTTP URL and pass it to your LlmAgent. This exposes tools like `object_detection` and `image_classification` to your Gemini models immediately.

Yes, your Google ADK agent can retrieve image URLs from BigQuery, pass them to `image_to_text`, and then write the generated descriptions back to your database.

Large images are handled efficiently by passing them as base64 strings or URLs to the MCP server. We recommend scaling down massive files before sending them to prevent hitting payload limits.

Yes, you can use the tool_names filter in McpToolset to limit exposure. For example, you can restrict an agent to only use `image_classification` while blocking resource-heavy tools like `image_segmentation`.

No visual data or base64 payloads are written to disk. The Vinkius sandbox processes your images in ephemeral memory, passing them securely to Hugging Face and returning the results to your Google ADK client before wiping the session clean.

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