Can my AI start a data extraction and let me know when it finishes?

Yes! You can ask your agent to `run_robot` on a certain URL. The agent receives the newly created task ID and can immediately invoke `get_task` sequentially to poll for completion. Once successful, it calls `get_task_data` to dump the JSON right into your conversation without breaking workflow.

How do bulk operations work natively through the agent?

When you have a trained robot, you can feed the `run_bulk_task` command an array of different URLs. Browse AI's backend splits them virtually into independent task instances. Your agent tracks the bulk run via `get_bulk_task` and eventually pulls the mega JSON merge using `download_bulk_data`.

Is there a risk of my agent suddenly spending all my API credits?

You have complete visibility—the agent can query `list_credits` at any moment to inform you precisely of your available balance and monthly limit. Also, since tools execute your natural directives, your AI agent only triggers extractions you specifically prompt for.

Browse AI MCP Server for Google ADK 10 tools — connect in under 2 minutes

Name: Browse AI
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 10 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Browse AI as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="browse_ai_1_agent",
    instruction=(
        "You help users interact with Browse AI "
        "using 10 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Browse AI MCP Server

Connect your Browse AI account to any AI agent and take full control of your no-code web scraping operations through natural conversation.

Google ADK natively supports Browse AI as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 10 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Robot Discovery — List all your trained extraction and monitoring robots along with their configuration details
Execute Scrapes — Trigger specific robots to run tasks on target URLs without lifting a finger
Data Retrieval — Instantly download the final extracted JSON data from any successfully completed task
Bulk Operations — Initiate multi-URL concurrent extractions and download the unified bulk datasets
Monitor Sync — Check the status of your active web change monitors
Quota Management — Retrieve your current API credits usage and monthly plan limits

The Browse AI MCP Server exposes 10 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Browse AI to Google ADK via MCP

Follow these steps to integrate the Browse AI MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 10 tools from Browse AI via MCP

Why Use Google ADK with the Browse AI MCP Server

Google ADK provides unique advantages when paired with Browse AI through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Browse AI

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Browse AI tools with BigQuery, Vertex AI, and Cloud Functions

Browse AI + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Browse AI MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Browse AI and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Browse AI tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Browse AI regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Browse AI

Browse AI MCP Tools for Google ADK (10)

These 10 tools become available when you connect Browse AI to Google ADK via MCP:

download_bulk_data

Returns a JSON array where each element contains the capturedData from one task. Download all extracted results from a completed Browse AI bulk run

get_bulk_task

Get bulk task execution status from Browse AI

get_robot

Get detailed configuration of a specific Browse AI robot

get_task

Check the status of a specific Browse AI extraction task

get_task_data

Only meaningful when the task status is "successful". Fields match the column names configured in the Browse AI robot builder hitting internal task references. Retrieve the final extracted JSON data from a successful Browse AI task

list_credits

Check Browse AI quota limits and credit usage

list_monitors

Monitors run on scheduled intervals to detect changes on target web pages and trigger notifications or data captures automatically via `/monitors`. List all active Browse AI web monitoring robots

list_robots

Each robot represents a no-code AI scraping workflow targeting a specific website or data pattern via `GET /robots`. List all Browse AI extraction and monitoring robots

run_bulk_task

Each set typically contains a different "originUrl". All extractions run concurrently on Browse AI infrastructure. Run a Browse AI robot in bulk mode across multiple URLs

run_robot

Pass a JSON string of input parameters (typically including "originUrl" for the target page and any variable fields the robot expects). Returns a taskId. Trigger a Browse AI robot to extract data from a target URL

Example Prompts for Browse AI in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Browse AI immediately.

"List all my robots. Which ones are built for monitoring?"

"Run my HackerNews Scraper robot on the main page."

"Retrieve the JSON data for task t-78ab31."

Troubleshooting Browse AI MCP Server with Google ADK

Common issues when connecting Browse AI to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Browse AI + Google ADK FAQ

Common questions about integrating Browse AI MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.