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

Q: How do I connect the ClickHouse (Vector Search) MCP Server to the Vercel AI SDK?

Install @ai-sdk/mcp and initialize the client using createMCPClient. Point the HTTP transport URL to your Vinkius endpoint, extract the tools with mcpClient.tools(), and pass them directly into streamText.

Build real-time vector search applications in Next.js using the Vercel AI SDK to stream ClickHouse results straight to your users.

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 Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query embeddings live with this MCP Server

Passing user input through `vector_search` using `streamText` pushes nearest neighbor matches into the DOM instantly. Streaming vector similarity results to a React frontend requires fast execution, and you don't wait for massive JSON payloads to parse. Calling `execute_sql` lets your Vercel AI SDK agent filter metadata alongside the embedding search. This pushes complex analytical data straight into your Svelte or Vue components exactly as it arrives from the cluster.

Introspect ClickHouse schemas dynamically

Calling `list_databases` and `list_tables` maps out the current database environment through the MCP before your Next.js app constructs queries. Hardcoding database structures breaks when your tables evolve, but the agent understands exactly what data exists right now. Running `describe_table` pulls the exact schema, letting your Edge Functions render dynamic tables. Getting specific column types matters for formatting UI components based on the real types returned by the cluster.

Monitor cluster health during generation

Your agent can check `get_table_stats` to verify row counts and memory usage before deciding to run an expensive aggregation. Long-running analytical queries strain your backend, and checking limits prevents timeouts on your Vercel Edge deployments. Firing `get_version` ensures your TypeScript code only attempts vector operations supported by the active ClickHouse runtime. Version compatibility dictates which HNSW index features you can use, and verifying it avoids unhandled exceptions in production.

Setup guide

Set up ClickHouse (Vector Search) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all ClickHouse (Vector Search) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent ClickHouse (Vector Search) transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the client using `createMCPClient`. Point the HTTP transport URL to your Vinkius endpoint, extract the tools with `mcpClient.tools()`, and pass them directly into `streamText`.

Yes, that is the primary advantage of this setup. When the agent triggers a vector search, the nearest neighbor distances and metadata stream chunk-by-chunk into your UI components without waiting for the full query to finish.

You can run this integration perfectly on the Edge. The HTTP transport layer makes lightweight requests to the MCP Server, bypassing the need for heavy native database drivers in your Next.js application.

Vinkius manages the actual database credentials within the isolated container. Your frontend code only needs a single Vinkius endpoint token, which you configure via the authProvider when setting up the HTTP transport.

Your vector arrays and SQL query strings never persist on our infrastructure. The Vinkius V8 Isolate Sandbox routes your commands directly to your database and destroys the execution context immediately after the HTTP connection closes.

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