How to Use the ClickHouse (Vector Search) MCP in Google ADK

Q: How do I initialize the ClickHouse (Vector Search) tools in Google ADK?

Use the McpToolset class with your Vinkius HTTP endpoint URL. Pass this toolset into your LlmAgent constructor to expose the database tools to Gemini.

Q: How does the agent handle large vector search payloads?

The vectorsearch tool returns compact JSON arrays containing distance scores and IDs. This keeps payload sizes low, saving your token budget for actual reasoning.

Connect your Google ADK agents to this ClickHouse (Vector Search) MCP Server for high-performance retrieval across massive context windows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ClickHouse (Vector Search) MCP to Google ADK

Create your Vinkius account to connect ClickHouse (Vector Search) 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 ClickHouse (Vector Search) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

High-dimensional similarity searches

The `vector_search` tool calculates mathematical distance traces to find matching embeddings inside your ClickHouse tables. This lets Gemini agents pull relevant context from millions of rows in a fraction of a second. Combined with `execute_sql`, your agent can grab raw vector matches and immediately join them with operational data. This gives your enterprise workflows complete context without leaving the database layer.

Schema mapping for Google ADK agents

The `describe_table` tool pulls structural properties and active column schemas for any target table. Your MCP client reads this structure to build precise, error-free queries. To prevent query failures, the agent runs `list_tables` to confirm table names exist before executing search operations. This step-by-step validation keeps long-context reasoning runs from failing on basic syntax errors.

Live cluster monitoring and health checks

The `get_table_stats` tool extracts internal database states to monitor table sizes and overall cluster health. Your agent uses this data to route queries away from overloaded nodes. With `get_version`, the agent checks for critical engine features like HNSW index support. This ensures your agent only attempts advanced vector searches on clusters that can run them.

Setup guide

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

Use the `McpToolset` class with your Vinkius HTTP endpoint URL. Pass this toolset into your `LlmAgent` constructor to expose the database tools to Gemini.

Yes. You can connect your agent using either transport method depending on your deployment architecture. HTTP is recommended for cloud-hosted environments.

Yes. Use the optional tool name filter when setting up your toolset. This prevents the agent from running structural commands like `execute_sql` if it only needs search capabilities.

The `vector_search` tool returns compact JSON arrays containing distance scores and IDs. This keeps payload sizes low, saving your token budget for actual reasoning.

Yes. All SQL commands and embedding vectors are processed inside an isolated, zero-trust V8 sandbox. Your credentials are encrypted at rest and never exposed to the LLM or external networks.

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