How to Use the Crawlbase MCP in Google ADK

Q: How can I use Crawlbase with Google ADK to pull social data into BigQuery?

Your agent calls tools like scrapefacebook or scrapetwitter to get the data. Then, using native Google ADK capabilities, it can parse that data and execute a BigQuery insert statement. The Crawlbase server just provides the initial web content.

Q: What's the best way to configure the Crawlbase tools for a Google ADK agent?

After your pip install, you'll create an McpToolset instance with your server URL. You can use the toolnames filter to explicitly declare which of the 10 Crawlbase tools your LlmAgent should have access to, which is great for building specialized agents.

Q: My agent needs to scrape Google search results. How does Crawlbase help?

Just have your agent call the scrapegoogleserp tool. It handles the complexity of making the request look like it's from a real user, so you get back the actual search results page data for your agent to parse.

Connect your Google ADK agent to live web data and feed it directly into your BigQuery tables.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crawlbase MCP to Google ADK

Create your Vinkius account to connect Crawlbase 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 Crawlbase with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Web Pages into BigQuery Rows

Give your Google ADK agent the ability to query the live web. It can use tools like `scrape_linkedin` for company profiles or `scrape_amazon` for market pricing. The agent gets structured data back, ready for processing. This is built for the Google Cloud ecosystem. An agent can scrape a list of target URLs, and with Gemini's massive context window, analyze all the results at once. Then, it can write the extracted information directly into a BigQuery table as part of the same workflow.

Use Your Google ADK Agent for Search Analysis

The `scrape_google_serp` tool lets your agent perform Google searches and get the raw results back. This is perfect for agents designed to track rankings, monitor brand mentions, or analyze competitor ad copy. You get the real search engine results page data, not a cleaned-up API version. Combine this with the power of Vertex AI. Your agent can gather SERP data over time, store it, and then use a Vertex AI model to spot trends. The Crawlbase MCP Server acts as the data source for your intelligent enterprise agents.

Reliable Scraping for Your Cloud Infrastructure

Your agent can handle any site, from simple HTML pages with `scrape_html` to complex single-page applications with `scrape_js_rendered`. Crawlbase manages the proxy infrastructure required to avoid blocks and timeouts, so your agent's requests succeed. When you build on Google Cloud, you need tools that are just as reliable. This MCP Server is managed by Vinkius, providing a stable endpoint for your agents. You can filter the exact tools you want to expose to your `LlmAgent`, giving you fine-grained control over its capabilities.

Setup guide

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

Your agent calls tools like `scrape_facebook` or `scrape_twitter` to get the data. Then, using native Google ADK capabilities, it can parse that data and execute a BigQuery insert statement. The Crawlbase server just provides the initial web content.

Yes, perfectly. Your agent can use Crawlbase to scrape dozens of pages, collect all the HTML or JSON content, and then feed that entire batch into a Gemini model for a comprehensive analysis in a single prompt.

After your pip install, you'll create an `McpToolset` instance with your server URL. You can use the `tool_names` filter to explicitly declare which of the 10 Crawlbase tools your `LlmAgent` should have access to, which is great for building specialized agents.

Just have your agent call the `scrape_google_serp` tool. It handles the complexity of making the request look like it's from a real user, so you get back the actual search results page data for your agent to parse.

Crawlbase only ever sees the URLs for the pages you're scraping, like Google SERPs or LinkedIn profiles. The Vinkius platform ensures each request runs in a zero-trust, isolated environment. The raw web content it fetches is passed back to your agent and not stored.

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