How to Use the data.world MCP in Google ADK

Q: How do I register the data.world MCP Server in Google ADK?

Run pip install google-adk and define your McpToolset using the Streamable HTTP transport parameters. Pass this toolset into your LlmAgent initialization to expose the catalog tools to Gemini.

Q: How does Google ADK handle user profile lookups in data.world?

The agent invokes getmyprofile to retrieve your username and display name. This ensures that any action Gemini takes on the platform is logged under your verified credentials.

Connect Gemini's million-token context to data.world using the Google ADK via a secure MCP connection.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect data.world MCP to Google ADK

Create your Vinkius account to connect data.world 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 data.world with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed data.world metadata into Gemini's long context

`get_dataset_details` extracts complete data.world field definitions and file listings to populate Gemini's massive context window. The Google ADK feeds this entire schema directly to the model, allowing deep reasoning over complex data.world catalogs. This setup bridges your BigQuery databases with external data.world definitions via Google ADK. Gemini compares the schemas side-by-side to identify missing fields or outdated tables without manual mapping.

Run catalog searches via Google ADK and MCP Server

`search_catalog` allows Gemini to execute full-text searches across your data.world titles, tags, and descriptions. Your Google ADK agent finds relevant datasets on the fly and immediately uses them to answer complex analytical prompts. You can restrict which tools Gemini sees by applying a `tool_names` filter in the Google ADK `McpToolset` configuration. This keeps your Google Cloud agent focused only on data.world catalog discovery and avoids unnecessary API calls.

Track project workspaces and team updates

`list_project_insights` retrieves documented findings and visualizations attached to your data.world projects via MCP. The Google ADK agent parses these insights and summarizes them for your team inside Google Cloud monitoring tools. To keep projects aligned, the Google ADK agent uses `get_project_details` to verify active members and resource statuses. It matches these data.world details against your internal directory to ensure correct access levels.

Setup guide

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

Run `pip install google-adk` and define your `McpToolset` using the Streamable HTTP transport parameters. Pass this toolset into your `LlmAgent` initialization to expose the catalog tools to Gemini.

Yes. Gemini can query your BigQuery datasets natively and then use `list_dataset_queries` to pull matching SQL patterns from data.world. This lets the model translate and join data across both platforms.

The agent invokes `get_my_profile` to retrieve your username and display name. This ensures that any action Gemini takes on the platform is logged under your verified credentials.

Yes, the toolset handles both transport layers. For production deployments on Google Cloud, we recommend using the Streamable HTTP transport for better scalability.

Yes, Vinkius handles authentication using a single-token entry point, preventing your API keys from leaking to Google Cloud logs. The server runs in a zero-trust environment where data is processed in-memory and never stored.

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