How to Use the CData Connect Cloud MCP in Google ADK

Q: How does CData Connect Cloud handle large tables with Google ADK?

The agent uses cdatagettablecolumns to discover table limits and fields first. It then writes optimized SQL queries to pull only the records needed, preventing token bloat in your Gemini context window.

Q: Can I isolate databases between different Google ADK agents?

Yes. You use cdatalistworkspaces to segment your data sources into distinct organizational groups. You then configure each agent to only access connections within its designated workspace.

Connect your Google ADK agents directly to your cloud databases and run SQL queries within your Gemini workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CData Connect Cloud MCP to Google ADK

Create your Vinkius account to connect CData Connect Cloud 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 CData Connect Cloud with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run direct SQL queries from Google ADK

`cdata_execute_query` is the tool your Google ADK agent uses to execute SQL queries directly against downstream databases. This allows your Gemini models to analyze live transactional data alongside your existing BigQuery datasets without manual exports. The agent pulls real-time tables on demand to ground its reasoning in actual database values. You get precise answers backed by live data instead of outdated static reports.

Explore database structures dynamically

`cdata_list_tables` is the tool your agent runs to inspect the available structural collections in your connected databases. Once it finds the right table, the agent invokes `cdata_get_table_columns` to read the exact schema definitions before drafting its SQL query. This workflow keeps your long-context Gemini agents from making assumptions about your database layout. By inspecting metadata first, the agent avoids syntax errors and retrieves only the necessary columns.

Manage database connections programmatically

`cdata_create_connection` is the tool that lets your agent configure new backend data source proxies dynamically. Using this MCP Server, your agent checks existing configurations with `cdata_list_connections` to see if the required database is already mapped. To verify that a newly created proxy is active and reachable, the agent runs `cdata_test_connection`. This ensures your automated data pipelines remain stable even when moving between different testing environments.

Setup guide

Set up CData Connect Cloud 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 CData Connect Cloud 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="CData Connect Cloud_agent",
    model="gemini-2.0-flash",
    instruction="You have access to CData Connect Cloud 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 CData Connect. 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 CData Connect Cloud 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 CData Connect Cloud MCP in Google ADK

You initialize the toolset using the HTTP transport URL provided by Vinkius. Once registered, your Gemini agent automatically detects tools like `cdata_execute_query` to run database tasks.

Yes, if your connection permissions allow it. The agent uses `cdata_execute_query` to run write operations, provided the underlying proxy credential has write access.

The agent uses `cdata_get_table_columns` to discover table limits and fields first. It then writes optimized SQL queries to pull only the records needed, preventing token bloat in your Gemini context window.

Yes. You use `cdata_list_workspaces` to segment your data sources into distinct organizational groups. You then configure each agent to only access connections within its designated workspace.

Your raw database credentials reside securely within your managed CData environment, never inside the Google ADK itself. The MCP Server acts as a zero-trust proxy, passing only raw query results back to your Gemini agent.

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