How to Use the Web Scraper MCP in Google ADK

Q: How does the Web Scraper integrate with Google ADK agents?

The read tool fetches full articles and converts them into clean Markdown. Your agent can then process this structured content directly within the Google Cloud workflow.

Q: Can I use Web Scraper in Google ADK to find internal links?

Yes, the listlinks tool extracts all hyperlinks from a page, but it only returns those that share the same hostname as the original source. This is great for linking within an established site structure.

Q: What metadata fields does Web Scraper provide in Google ADK?

You get robust structured data using extract. Fields include title, description, Open Graph tags, detected language (lang), and whether the page has a canonical tag. This covers most basic web identity needs.

Q: Is Web Scraper good for reading long-form content with Google ADK?

The read tool is designed exactly for this. It uses Reader View principles to strip away clutter and return the core article body as clean Markdown, perfect for large context models.

Scrape data and structure web content using the Web Scraper with Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Web Scraper MCP to Google ADK

Create your Vinkius account to connect Web Scraper 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 Web Scraper with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Extract Structured Metadata via MCP Server

The `extract` tool pulls structured metadata from any page. You get title, description, OG tags, and more without needing to download the full content. This is great for cataloging or auditing web resources. It lets your agent check critical details—like if a link is canonical or what language the author used—saving you time on manual data collection.

Crawl Documentation Sites with Google ADK

Need to map out an entire site? The `crawl` tool traverses a website, starting from one URL. It limits the exploration to 10 pages maximum to keep things clean. This process helps your agent build a navigational understanding of documentation or help centers without needing complex external mapping tools.

Bulk Reading with Web Scraper

The `batch_read` tool fetches multiple web pages in parallel, up to 10 URLs at once. This function is key for ingesting data from a defined list of sources. Since it runs requests simultaneously, your agent processes information much faster than if it had to wait for each page fetch to complete sequentially.

Setup guide

Set up Web Scraper 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 Web Scraper 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="Web Scraper_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Web Scraper 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 Web Scraper. 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 Web Scraper 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 Web Scraper MCP in Google ADK

The `read` tool fetches full articles and converts them into clean Markdown. Your agent can then process this structured content directly within the Google Cloud workflow.

Yes, the `list_links` tool extracts all hyperlinks from a page, but it only returns those that share the same hostname as the original source. This is great for linking within an established site structure.

You get robust structured data using `extract`. Fields include title, description, Open Graph tags, detected language (`lang`), and whether the page has a canonical tag. This covers most basic web identity needs.

The `read` tool is designed exactly for this. It uses Reader View principles to strip away clutter and return the core article body as clean Markdown, perfect for large context models.

This server touches structured metadata like titles, descriptions, Open Graph tags, author information, link counts, and canonical URLs. This helps your agent verify the page's core identity.

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