How to Use the ClickHouse (Vector Search) MCP in Mastra AI

Q: How do I configure Mastra AI to use the ClickHouse (Vector Search) MCP Server?

Install @mastra/mcp and instantiate a new MCPClient with your Vinkius endpoint URL. Mastra automatically detects the streamable HTTP transport layer, letting you spread the tools directly into your agent definition.

Automate complex analytical workflows and vector matching pipelines using Mastra AI to handle ClickHouse operations.

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 Mastra AI

Create your Vinkius account to connect ClickHouse (Vector Search) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build resilient pipelines with this MCP Server

Wrapping `execute_sql` inside a Mastra AI workflow gives you automatic exponential backoff. Analytical queries fail when clusters get overloaded. If the database drops the connection, your agent waits and tries the aggregation again without crashing the entire run. Running `get_table_stats` tells the workflow if a table is too large for a standard scan. Conditional logic based on cluster limits prevents failures, prompting the agent to switch strategies and use vector search with strict distance thresholds instead.

Map database schemas automatically

The agent calls `list_databases` and `list_tables` at the start of a run to verify the target environments exist. Workflows need accurate context to write valid SQL. It halts the process early if the expected logging tables are missing. By invoking `describe_table`, Mastra AI learns the precise column types. Extracting structural properties prevents syntax errors down the line, ensuring the workflow formats timestamps and integer arrays correctly before pushing arbitrary DML commands.

Verify vector index compatibility

Your MCP workflow can fire `get_version` to check the active runtime capabilities. Different ClickHouse versions support different HNSW index parameters. The agent dynamically adjusts its embedding queries to match the exact mathematical distance traces supported by that specific cluster. You can configure human-in-the-loop approvals for any raw DDL statements generated by the agent. Manual oversight keeps destructive queries in check, ensuring an admin reviews the structural changes before the workflow commits them to production.

Setup guide

Set up ClickHouse (Vector Search) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All ClickHouse (Vector Search) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "clickhouse-vector-search-mcp-client",
  servers: {
    "clickhouse-vector-search-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "ClickHouse (Vector Search) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to ClickHouse (Vector Search) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent ClickHouse (Vector Search) transactions"
);
console.log(result.text);

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 Mastra AI

Install `@mastra/mcp` and instantiate a new `MCPClient` with your Vinkius endpoint URL. Mastra automatically detects the streamable HTTP transport layer, letting you spread the tools directly into your agent definition.

Yes, built-in exponential backoff handles temporary cluster unavailability. If a massive SQL aggregation times out, the workflow engine pauses and re-attempts the operation based on your configured retry logic.

Manual oversight prevents accidental data deletion. Mastra lets you flag specific tools for human-in-the-loop review, pausing the workflow until an administrator approves the database modification.

The workflow dynamically inspects the environment using the MCP tools. It runs discovery queries to map out schemas and column types, allowing the agent to construct valid analytical payloads without hardcoded structures.

The exact query strings, mathematical vectors, and row metadata pass through an ephemeral V8 sandbox. Vinkius maintains a zero-trust architecture, meaning no persistent storage retains your database credentials or the contents of your analytical payloads.

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