How to Use the Browserbear MCP in Google ADK

Q: How do I configure the Browserbear toolset in my Google ADK project?

Install google-adk and define an McpToolset pointing to your managed Vinkius HTTP URL. This acts as your MCP interface.

Q: Can Gemini models in Google ADK analyze images generated by Browserbear?

Yes, the takescreenshot tool provides direct image URLs that Gemini parses instantly. This fits perfectly with the model's native multimodal capabilities.

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

Yes, the McpToolset constructor accepts an optional toolnames filter. You can restrict your agent to only use takescreenshot while blocking destructive tools like deleterun.

Feed live browser screenshots and scraped web data into your Google ADK pipelines for enterprise-grade Gemini reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserbear MCP to Google ADK

Create your Vinkius account to connect Browserbear 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 Browserbear with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed real-time web data into your Google ADK agent with MCP

The `take_screenshot` tool captures instant visual snapshots of any webpage to feed directly into Gemini's massive 1M token context window. Google ADK agents analyze these images alongside structured BigQuery tables to detect visual anomalies or track competitor pricing changes. Using raw screenshots avoids the mess of cleaning raw HTML. Your Gemini model processes the visual layout directly, matching what a human user sees on the screen.

Run complex browser flows via Google ADK and MCP

The `run_task` tool starts multi-step browser automations that you can monitor directly from your Vertex AI console. Google ADK coordinates these runs, allowing your agent to trigger a task and then wait for the output before proceeding. You check execution statuses using `get_run` to ensure your enterprise workflows never stall. If a task fails, your agent automatically logs the failure directly to Cloud Logging.

Manage project assets with this Google ADK MCP Server

The `list_projects` tool fetches all active workspaces within your Browserbear account. Google ADK uses this tool to organize your automated runs, ensuring that scraped data lands in the correct enterprise bucket. Your agent uses `list_tasks` to discover available automation templates on the fly. This dynamic discovery lets you scale your scraping operations without hardcoding task IDs.

Setup guide

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

Install `google-adk` and define an `McpToolset` pointing to your managed Vinkius HTTP URL. This acts as your MCP interface.

Yes, the `take_screenshot` tool provides direct image URLs that Gemini parses instantly. This fits perfectly with the model's native multimodal capabilities.

All authentication is handled at the Vinkius gateway level using secure single-token endpoints. Your Google Cloud environment never needs to store or expose raw Browserbear API keys.

Yes, the `McpToolset` constructor accepts an optional `tool_names` filter. You can restrict your agent to only use `take_screenshot` while blocking destructive tools like `delete_run`.

Your browser screenshots and scraped text stay inside the secure Browserbear cloud infrastructure. Google ADK only retrieves temporary signed URLs and JSON payloads, keeping your enterprise data footprint minimal.

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