How to Use the Materialize (Streaming SQL DB) MCP in Google ADK

Q: How do I register Materialize (Streaming SQL DB) with the Google ADK?

Install google-adk and point your MCP Server to your Vinkius HTTP URL. Pass this toolset into your LlmAgent constructor to expose the streaming database tools to Gemini.

Q: Can I limit the tools my Google ADK agent can access on Materialize (Streaming SQL DB)?

Yes. Use the optional tool names filter in the McpToolset configuration to restrict the agent to read-only commands. This prevents the agent from calling createcluster or executing destructive schema changes.

Run real-time streaming SQL queries alongside your BigQuery pipelines using the Google ADK and Gemini models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Materialize (Streaming SQL DB) MCP to Google ADK

Create your Vinkius account to connect Materialize (Streaming SQL DB) 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 Materialize (Streaming SQL DB) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run streaming SQL queries alongside BigQuery

The `execute_sql` tool pulls real-time updates from Materialize while your Gemini model references historical data in BigQuery. This setup gives your enterprise agent immediate access to live events alongside deep historical context. Gemini handles the long-context reasoning over these combined streams, processing up to 1M tokens of operational logs. You get instant answers from active streams without waiting for traditional batch ETL processes.

Scale streaming compute via Google ADK

The `create_cluster` tool provisions isolated compute nodes to handle sudden spikes in streaming ingestion. Your agent chooses sizes from xs to xl to handle traffic spikes during enterprise ingestion windows. Running `list_clusters` lets the agent audit active compute nodes directly from its execution loop. This helps you monitor infrastructure spend and shut down idle compute resources when real-time pipelines finish processing.

Verify pipeline uptime using this MCP Server

The `check_health` tool monitors the uptime and connection status of your active streaming pipelines. Your agent checks this status before pulling data to ensure downstream systems receive fresh metrics. If the connection lag spikes, your Google ADK agent alerts your operations team or switches to backup data sources. This active monitoring keeps your automated decisions grounded in actual, real-time metrics.

Setup guide

Set up Materialize (Streaming SQL DB) 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 Materialize (Streaming SQL DB) 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="Materialize (Streaming SQL DB)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Materialize (Streaming SQL DB) 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 Materialize. 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 Materialize (Streaming SQL DB) 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 Materialize (Streaming SQL DB) MCP in Google ADK

Install `google-adk` and point your MCP Server to your Vinkius HTTP URL. Pass this toolset into your `LlmAgent` constructor to expose the streaming database tools to Gemini.

Yes. Use the optional tool names filter in the `McpToolset` configuration to restrict the agent to read-only commands. This prevents the agent from calling `create_cluster` or executing destructive schema changes.

Materialize processes continuous streaming queries with millisecond latency, whereas BigQuery is optimized for analytical batch queries. Your Google ADK agent coordinates both to balance real-time action with deep historical analysis.

The MCP Server supports both Stdio and Streamable HTTP transports. For cloud-native deployments on Google Cloud, the HTTP transport offers the most stable connection to your Vinkius gateway.

All communication runs through a zero-trust V8 isolate sandbox on Vinkius. The MCP Server only handles the specific SQL strings and cluster metadata commands you execute, ensuring your database credentials never leak into public LLM training sets.

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