How to Use the MyScale (SQL Vector Database API) MCP in Google ADK

Q: Is MyScale (SQL Vector Database API) compatible with Google ADK for vector search?

Yes. You can use the vectorsearch tool to perform similarity lookups. It integrates directly into the toolset passed to your LlmAgent.

Q: How does Google ADK handle index monitoring for MyScale (SQL Vector Database API)?

You use checkindexstatus as a tool call. The response tells your agent if the index is ready, in progress, or failed.

Q: Can I mix SQL and vector search in MyScale (SQL Vector Database API) with Google ADK?

Yes. You can use executesqlquery for relational data and vectorsearch for semantic data. Both work through the same MCP connection.

Q: How do I verify the cluster is reachable?

Invoke pingcluster before your main task. It's a quick way to ensure your agent doesn't waste tokens on a dead connection.

Integrate vector search into your Google ADK agents using familiar SQL.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MyScale (SQL Vector Database API) MCP to Google ADK

Create your Vinkius account to connect MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct SQL access with Google ADK

Your agent needs to query data, not learn a new API. Use `execute_sql_query` to run standard statements against your tables, keeping your logic tied to the SQL you already know. This bypasses the need for complex middleware. You'll keep your Google ADK agent focused on reasoning while the database handles the retrieval.

Automated indexing inside Google ADK

You can now define your vector indices through your agent's toolset. Use `create_vector_index` to set up your search space and `check_index_status` to verify it's ready. Keep your infrastructure as code. By managing these lifecycle tasks through your agent, you ensure your search indices are always in the state you expect.

Vector similarity with Google ADK

Perform searches by calling `vector_search` directly from your agent's workflow. It returns the results as JSON, which your agent can immediately process for Gemini's long-context window. This is the fastest way to get semantic results into your agent's memory. No need to manually build the join logic, just call the tool and get your vectors back.

Setup guide

Set up MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) 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="MyScale (SQL Vector Database API)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to MyScale (SQL Vector Database API) 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 MyScale. 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 MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) MCP in Google ADK

Yes. You can use the `vector_search` tool to perform similarity lookups. It integrates directly into the toolset passed to your LlmAgent.

You use `check_index_status` as a tool call. The response tells your agent if the index is ready, in progress, or failed.

Yes. You can use `execute_sql_query` for relational data and `vector_search` for semantic data. Both work through the same MCP connection.

Invoke `ping_cluster` before your main task. It's a quick way to ensure your agent doesn't waste tokens on a dead connection.

The server uses standard transport encryption. It only touches your schema and query results, never storing your vector embeddings or sensitive text locally.

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