How to Use the Hugging Face LLM MCP in Google ADK

Q: How do I configure Hugging Face LLM within a Google ADK agent?

Install the ADK using pip install google-adk and initialize your tools. Create an McpToolset using StreamableHttpServerParameters with your Vinkius URL, then pass it to the tools list of your LlmAgent. This exposes the Hugging Face tools to your Gemini models.

Q: Can Google ADK use Hugging Face LLM for sentiment analysis?

Yes, your Google ADK agent can call the sentimentanalysis tool to evaluate user reviews or feedback. This offloads sentiment scoring to open-source models, reserving your Vertex AI models for high-level reasoning. The agent receives the positive or negative classification directly in its tool execution loop.

Q: How does Hugging Face LLM handle translation inside Google ADK?

The agent calls the translatetext tool, passing the target language and the source text. The MCP server runs the translation on specialized open-source models and returns the result. This is highly effective for processing multilingual datasets pulled directly from BigQuery.

Connect Hugging Face LLM to your Google ADK pipelines and analyze BigQuery data with open-source models.

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 LLM MCP to Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scale BigQuery workflows with this MCP Server

Google ADK agents often process massive datasets stored in Google Cloud. Instead of running expensive proprietary models over millions of rows, use this MCP server to route basic NLP tasks to Hugging Face. Your agent can pull text from BigQuery and run `classify_text` to categorize records at scale. This setup keeps your Vertex AI costs down. The agent uses the `LlmAgent` class to run the workflow, passing the Vinkius HTTP endpoint to `McpToolset` so the agent can access open-source models directly.

Long-context reasoning with Gemini and Hugging Face

Gemini models in Google ADK can hold over a million tokens of context. You can feed massive documents into Gemini, then let it call `extract_entities` or `summarize_text` via the MCP toolset to process specific sections. This combines Gemini's huge memory with fast, specialized open-source models. If your pipeline needs to fill in missing document values, the agent calls `fill_mask` to run masked language modeling. You configure this by passing the toolset parameters to the Google ADK agent, which manages the transport layer automatically.

Sentiment and QA tools for enterprise pipelines

Build enterprise customer service pipelines that run on Google Cloud infrastructure. Your Google ADK agent can analyze incoming emails by calling `sentiment_analysis` to flag urgent issues. If the email contains a technical support question, the agent uses `answer_question` to extract answers from your internal documentation. For international markets, the agent calls `translate_text` to normalize incoming data before storing it in your cloud database. You can filter which tools are exposed to the agent by setting the optional tool names filter in your ADK configuration.

Setup guide

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

Install the ADK using `pip install google-adk` and initialize your tools. Create an `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL, then pass it to the `tools` list of your `LlmAgent`. This exposes the Hugging Face tools to your Gemini models.

Yes, your Google ADK agent can call the `sentiment_analysis` tool to evaluate user reviews or feedback. This offloads sentiment scoring to open-source models, reserving your Vertex AI models for high-level reasoning. The agent receives the positive or negative classification directly in its tool execution loop.

The agent calls the `translate_text` tool, passing the target language and the source text. The MCP server runs the translation on specialized open-source models and returns the result. This is highly effective for processing multilingual datasets pulled directly from BigQuery.

Yes, the Google ADK toolset configuration supports an optional filter to limit exposed tools. If you only want your agent to perform text generation, you can restrict the toolset to only expose `text_generation`. This prevents the agent from making unnecessary tool calls.

Your enterprise prompts, context blocks, and database strings processed by tools like `extract_entities` or `fill_mask` are safe. Vinkius runs the MCP server in a zero-trust, ephemeral V8 sandbox. No text data is cached or used for training, ensuring your Google Cloud data pipeline remains secure.

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