How to Use the Grepsr MCP in Google ADK

Q: Can Gemini use Google ADK to filter specific scraping records from Grepsr?

Yes, it can. The agent can call getreportdata with specific query parameters to filter the extracted records. This lets Gemini process only the relevant rows, saving token costs and reducing memory overhead.

Q: How does Google ADK handle long-running Grepsr scraping tasks?

Your agent can trigger the crawler using runreport and monitor its progress by querying getreporthistory. For long runs, configuring a webhook via createwebhook is the most reliable approach.

Feed clean web data straight into BigQuery and Gemini with the Google ADK integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Grepsr MCP to Google ADK

Create your Vinkius account to connect Grepsr 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 Grepsr with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Crawls from Gemini Pipelines

The `run_report` tool allows your Gemini-powered agents to start web extraction runs using our MCP standard. When a user asks for updated market pricing, the agent initiates the crawler immediately. Once finished, the agent uses `get_latest_data` to pull the raw text directly into its context window. This matches Gemini's massive token capacity, letting you process thousands of scraped rows in one go.

Sync Web Scraping with Google ADK Data Pipelines

The `list_integrations` tool lets your enterprise agent verify where scraping outputs are being shipped. You can confirm that your data lands in Google Cloud Storage or other active endpoints before starting downstream BigQuery processing. By calling `get_report_data`, your agent can query specific records directly from past runs. This eliminates manual ETL steps, keeping your analytical databases updated with fresh web inputs automatically.

Configure Real-time Web Extraction Triggers

The `create_webhook` tool lets your enterprise agent set up immediate notifications for completed scraping runs. Instead of constantly polling for updates, your agent configures a webhook to alert your GCP cloud functions. This MCP Server setup lets you build event-driven pipelines that only run when new data is ready. You can inspect existing configurations at any time using `list_webhooks` to keep your event architecture clean.

Setup guide

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

Initialize the toolset using McpToolset with your Vinkius HTTP URL. Pass this object to your LlmAgent in the tools parameter, allowing Gemini models to auto-discover the scraping functions.

Yes, it can. The agent can call `get_report_data` with specific query parameters to filter the extracted records. This lets Gemini process only the relevant rows, saving token costs and reducing memory overhead.

Your agent can trigger the crawler using `run_report` and monitor its progress by querying `get_report_history`. For long runs, configuring a webhook via `create_webhook` is the most reliable approach.

Yes. You can use the optional tool names filter in the MCP integration to restrict agent access. This allows you to expose only data reading tools like `get_latest_data` while hiding configuration tools.

Vinkius handles your extraction tokens inside a zero-trust, ephemeral environment. The Google ADK agent only interacts with the exposed MCP tools, ensuring your credentials and scraped reports are never exposed to the LLM or public logs.

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