How to Use the MindsDB (AI Database & Predictors) MCP in Google ADK

Q: Can I use MindsDB (AI Database & Predictors) with Google ADK for BigQuery data?

Yes, you can query BigQuery data by using executesqlquery through the agent toolset. The agent can join your Google Cloud data with predictive models in a single SQL step.

Q: How do I check if a predictive model is online in MindsDB (AI Database & Predictors) using Google ADK?

Your agent calls listmodels to check the active predictors in the system. It can then use getmodel to inspect the training metrics before executing predictions.

Connect your enterprise Google ADK agents to predictive SQL models and connected databases.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MindsDB (AI Database & Predictors) MCP to Google ADK

Create your Vinkius account to connect MindsDB (AI Database & Predictors) 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 MindsDB (AI Database & Predictors) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context predictive SQL in Google ADK

The `execute_sql_query` tool exposes database prediction tables directly to your Gemini-powered Google ADK agents via this MCP Server. Because Gemini handles massive token lengths, your agent can process larger result sets, though appending LIMIT rules remains a best practice to keep database CPU usage low. This setup allows your agent to join BigQuery tables with predictive models in a single step. You pass the server parameters to the toolset, and the agent executes the queries via HTTP or Stdio transports.

Model auditing and pipeline validation

The `list_models` tool lets your Google ADK agent audit active Vertex AI or MindsDB-hosted predictors to select the right forecasting engine. If the agent needs to inspect a model's internal metadata, it runs `get_model` to verify training status. This validation step ensures your agent never queries an uninitialized model. You can restrict the agent's scope by filtering the exposed tool names during initialization.

Data source mapping and health checks

The `list_databases` tool lists every external data source connected to your instance, letting the agent cross-reference cloud databases. For virtual representations of your data, `list_views` retrieves the active virtual views. These tools work together to let your agents map the data environment. If a connection drops, checking `get_status` over MCP gives the agent diagnostic metrics.

Setup guide

Set up MindsDB (AI Database & Predictors) 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 MindsDB (AI Database & Predictors) 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="MindsDB (AI Database & Predictors)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to MindsDB (AI Database & Predictors) 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 MindsDB. 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 MindsDB (AI Database & Predictors) 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 MindsDB (AI Database & Predictors) MCP in Google ADK

Yes, you can query BigQuery data by using `execute_sql_query` through the agent toolset. The agent can join your Google Cloud data with predictive models in a single SQL step.

The ADK loads the tools automatically when you register the MCP endpoint. You can also apply a tool name filter to expose only the specific operations your agent needs.

Your agent calls `list_models` to check the active predictors in the system. It can then use `get_model` to inspect the training metrics before executing predictions.

Yes, the ADK handles both connection methods. You configure the transport type in the server parameters depending on whether you run the agent locally or in the cloud.

Vinkius executes the server inside an ephemeral, zero-trust sandbox that isolates your database connection strings and schema structures. Only the specific query payloads requested by the agent are transmitted over the secure tunnel, keeping your cloud infrastructure secure.

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