How to Use the Browse AI MCP in Google ADK

Q: How do I initialize the Browse AI MCP Server in Google ADK?

Use McpToolset with your Vinkius HTTP URL. Pass that toolset instance directly into your LlmAgent tools parameter to expose the scraping capabilities.

Q: Can I restrict which Browse AI tools my Google ADK agent can access?

Yes. Use the toolnames filter in your McpToolset setup. You can limit your agent to read-only actions like listtasks and block write actions like createmonitor.

Q: How does Google ADK handle large bulk runs from Browse AI?

The ADK passes the raw JSON from getbulkrun to Gemini. Because Gemini supports long context windows, it can process massive scraped datasets without hitting token limits.

Feed live web data directly into your Gemini long-context models using Google ADK and Browse AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browse AI MCP to Google ADK

Create your Vinkius account to connect Browse AI 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 Browse AI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct Data Extraction with Google ADK

Your Gemini agent initiates real-time scraping by invoking `run_robot` to capture target website data. The Google ADK handles the HTTP transport for this MCP Server, pulling the structured JSON via `get_task` so your agent can format it for immediate BigQuery ingestion. With Gemini's massive context window, you don't need to summarize the output. The agent dumps the complete payload from `get_bulk_run` straight into the LLM context, making enterprise-grade web intelligence instantly searchable.

Control Browse AI Monitors from Gemini Agents

Keep your Vertex AI pipelines updated by allowing your agent to call `create_monitor` on schedule. The agent inspects existing setups using `list_monitors` and verifies queue health with `get_system_status` before triggering new extraction pipelines. By restricting the tools array in your `McpToolset` configuration, you control exactly which actions your enterprise agent can execute. Stop the agent from editing monitors while still allowing it to call `run_robot`.

Discover Approved Robots via Google ADK MCP Server

Your agent queries `list_robots` to find active scrapers deployed in your account. Once it identifies the correct target, it retrieves configuration details via `get_robot` and runs the extraction task. This dynamic lookup ensures your cloud workflows don't break when scrapers are updated. The ADK maps these tools into native functions that your Gemini models call with high accuracy.

Setup guide

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

Use `McpToolset` with your Vinkius HTTP URL. Pass that toolset instance directly into your `LlmAgent` tools parameter to expose the scraping capabilities.

Yes. Use the `tool_names` filter in your `McpToolset` setup. You can limit your agent to read-only actions like `list_tasks` and block write actions like `create_monitor`.

The ADK passes the raw JSON from `get_bulk_run` to Gemini. Because Gemini supports long context windows, it can process massive scraped datasets without hitting token limits.

Yes, the Google ADK handles both transports for this MCP Server. For Vinkius, you will configure it using the streamable HTTP transport parameters pointing to your hosted endpoint.

Your extracted web content and scraping task logs run within Vinkius's isolated sandbox. The Google ADK communicates via encrypted HTTP, ensuring that your scraped payloads never touch unverified public networks before reaching your GCP environment.

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