How to Use the HTML DOM Query Engine MCP in Google ADK

Turn your Google ADK agents into precision web scrapers by extracting specific DOM elements from massive payloads.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HTML DOM Query Engine MCP to Google ADK

Create your Vinkius account to connect HTML DOM Query Engine 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 HTML DOM Query Engine with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Extract elements inside Gemini workflows

Gemini models handle massive context windows, but feeding them raw HTML wastes compute. You want your Google ADK agent to pinpoint data fast. The `query_dom` tool lets the agent execute standard CSS selectors against raw HTML strings. You pass the markup and a selector like "#title" or ".product-price". The engine traverses the DOM and returns just the target text or attributes. It is deterministic, fast, and keeps your prompts focused on logic rather than parsing.

Connect the MCP Server via HTTP

Wiring this up in Google ADK takes a few lines of Python. You initialize McpToolset using StreamableHttpServerParameters and point it to your Vinkius URL. Then you pass that toolset to your LlmAgent constructor. If you want to restrict what the agent can do, you can use the optional tool names filter. This keeps the agent focused solely on DOM querying, preventing it from hallucinating other capabilities.

Feed clean data to BigQuery

Enterprise agents usually need to store their findings. Your agent can pull raw HTML from a cloud bucket, run the query engine to extract the specific nodes, and pipe that structured data directly into BigQuery. This isolates the messy parsing logic from your storage layer. The agent handles the extraction using familiar CSS syntax, ensuring only clean, validated text enters your Google Cloud data warehouse.

Setup guide

Set up HTML DOM Query Engine 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 HTML DOM Query Engine 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="HTML DOM Query Engine_agent",
    model="gemini-2.0-flash",
    instruction="You have access to HTML DOM Query Engine 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 Cheerio DOM. 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 HTML DOM Query Engine 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 HTML DOM Query Engine MCP in Google ADK

Install google-adk. Create an McpToolset with your Vinkius endpoint and pass it to the tools array of your LlmAgent.

No. The engine strictly uses CSS selectors to find elements. You pass queries like div > p.content to extract the exact text you need.

Yes, your agent just needs to read the file into a string first. It then passes that string to the `query_dom` tool along with the target selector.

Speed and cost. Forcing an LLM to read a massive DOM tree wastes tokens and slows down the response. Deterministic parsing is always faster.

Vinkius executes every request in an ephemeral sandbox. Your raw markup and extracted text nodes are processed in memory and immediately discarded. No logs retain your proprietary DOM structures.

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