How to Use the Knoema MCP in Google ADK

Q: How do I initialize the Knoema tools in Google ADK?

Import McpToolset from the SDK and configure it with your Vinkius HTTP endpoint. Pass this toolset into the tools parameter of your LlmAgent to expose these MCP tools to Gemini.

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

Yes, you can use the optional tool names filter in the McpToolset configuration. This lets you restrict access to read-only tools like searchdatasets if you want to prevent agents from pulling heavy time-series data.

Q: What tools should I use to check data units and frequencies?

Use listdataunits and listdatafrequencies to understand the scale and timing of the dataset. These tools ensure your agent does not compare monthly percentages with annual absolute values.

Feed global economic datasets directly into your Gemini models and BigQuery tables using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Knoema MCP to Google ADK

Create your Vinkius account to connect Knoema 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 Knoema with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed global statistics to Gemini via Google ADK

Gemini's million-token context window is built for deep historical analysis. By configuring this MCP Server with Google ADK, your agent can ingest decades of economic indicators using `get_data_series` and analyze them alongside your private BigQuery datasets. The agent uses `list_data_frequencies` to match the time intervals of Knoema statistics with your internal corporate timelines. This allows your LLM to perform massive cross-referencing tasks that would crash smaller context models.

Locate precise indicators with this MCP Server

Finding a needle in a haystack of global statistics is simple because this MCP Server makes finding specific metrics painless. Your Google ADK agent can programmatically search across thousands of datasets using `search_data_series` to pull specific metrics like regional inflation rates or agricultural yields. Once the correct series is found, the agent uses `get_dataset_metadata` to verify the source's authority. This metadata can be written directly to Vertex AI metadata stores for enterprise-grade lineage tracking.

Map global demographics and regional metrics

Your agent can instantly map out geographic data availability using this MCP connection. The `list_dataset_regions` tool lets the Google ADK agent confirm which countries or states are present in a dataset before pulling raw figures. If the required regions are present, the agent calls `get_latest_dataset_data` to populate your localized reports. This automation eliminates manual data gathering for global operations teams.

Setup guide

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

Import `McpToolset` from the SDK and configure it with your Vinkius HTTP endpoint. Pass this toolset into the `tools` parameter of your `LlmAgent` to expose these MCP tools to Gemini.

Yes, you can use the optional tool names filter in the `McpToolset` configuration. This lets you restrict access to read-only tools like `search_datasets` if you want to prevent agents from pulling heavy time-series data.

Gemini's large context window easily digests the massive JSON payloads returned by `get_data_series`. The Google ADK handles the stream transport, delivering raw statistical tables directly into the model's active memory.

Use `list_data_units` and `list_data_frequencies` to understand the scale and timing of the dataset. These tools ensure your agent does not compare monthly percentages with annual absolute values.

Absolutely. Vinkius handles authentication with a single secure token, routing all requests for statistical metadata and time-series indicators through ephemeral sandboxes. Your proprietary search queries are never exposed to external networks or cached.

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