How to Use the JigsawStack MCP in Google ADK

Q: How do I configure the JigsawStack MCP Server with Google ADK?

Install google-adk and use McpToolset with your Vinkius HTTP transport URL. Pass this toolset to your LlmAgent constructor to expose the tools.

Q: Can I limit which JigsawStack tools my Google ADK agent can access?

Yes, you can. Use the toolnames filter in your McpToolset configuration to expose only specific tools like aiwebscrape while hiding the moderation features.

Q: How does JigsawStack handle large texts with Google ADK?

The summarizetext tool condenses long documents before passing them to your agent. This reduces token usage when feeding large datasets into your Google ADK agent.

Q: What happens to the images and text processed by JigsawStack?

Images evaluated by checknsfwimage and web content extracted via aiwebscrape are processed over TLS and never cached on disk. The MCP Server runs inside an isolated, zero-trust sandbox to guarantee enterprise-grade data isolation.

Connect Gemini models to JigsawStack using Google ADK and this MCP Server to scrape the web and run OCR across your enterprise cloud data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JigsawStack MCP to Google ADK

Create your Vinkius account to connect JigsawStack 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 JigsawStack with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scale OCR across BigQuery with Google ADK

The `extract_text_from_image` tool runs visual OCR on image URLs retrieved from your BigQuery tables. Your Google ADK agent processes these images directly, reading text data and saving the structured output back into your cloud storage. This setup avoids complex pipeline glue. Because the Gemini models have a massive context window, you can feed entire batches of OCR text into a single run without hitting memory limits.

Semantic web search for Gemini agents

The `ai_web_search` tool queries the live web to find up-to-date information for your enterprise pipelines. Your Google ADK agent uses these search results to ground its answers, pulling fresh data directly into your Vertex AI workflow. For specific pages, the `ai_web_scrape` tool extracts raw content using plain English instructions. This lets your agent target specific data points on a competitor's site without writing brittle scraping rules.

Automated content moderation and translation

The `check_profanity_text` tool scans user inputs for offensive language before your agent processes them. This MCP integration keeps your Google ADK pipelines clean, ensuring only validated text reaches your downstream Vertex models. You can also use `translate_text` to handle multi-language support. The tool translates text blocks instantly, letting your agent communicate with global users without relying on external translation API setups.

Setup guide

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

Install `google-adk` and use `McpToolset` with your Vinkius HTTP transport URL. Pass this toolset to your `LlmAgent` constructor to expose the tools.

Yes, you can. Use the `tool_names` filter in your `McpToolset` configuration to expose only specific tools like `ai_web_scrape` while hiding the moderation features.

The `summarize_text` tool condenses long documents before passing them to your agent. This reduces token usage when feeding large datasets into your Google ADK agent.

The Google ADK toolset supports both Stdio and HTTP transports. For hosted Vinkius servers, you will use the HTTP transport with your secure endpoint token to access the MCP tools.

Images evaluated by `check_nsfw_image` and web content extracted via `ai_web_scrape` are processed over TLS and never cached on disk. The MCP Server runs inside an isolated, zero-trust sandbox to guarantee enterprise-grade data isolation.

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