An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Clickhouse Vector Search to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Query your clusters and run vector searches through natural language.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through ClickHouse.

  1. 01

    List databases

    This capability identifies the top-level logical arrays that manage your ClickHouse schemas.

  2. 02

    Describe table

    Use this to extract the specific properties and column schemas of a table.

  3. 03

    Get version

    This capability checks your active cluster limits and runtime version to confirm feature support.

  4. 04

    Execute SQL

    This capability runs arbitrary DML, DDL, or SELECT queries against your cluster.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through ClickHouse.

  1. 05

    Get table stats

    Use this to pull internal structural states and cluster health metrics.

  2. 06

    List tables

    This capability retrieves the specific tables available within a given database.

  3. 07

    Vector search

    This capability performs mathematical distance traces to route your vector embeddings.

Real work

What teams actually run

01

Semantic Search Debugging

Test how your vector embeddings behave by running similarity searches through the agent.

02

Automated Reporting

Ask your agent to run SELECT queries and summarize analytical data instantly.

03

Database Auditing

Check table compression and row counts to ensure your cluster is performing as expected.

04

Schema Prototyping

Quickly verify table structures and column types during the development phase.

Automate a task

Put ClickHouse to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

ClickHouse works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put ClickHouse to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

929ms average. Fast in production.

ClickHouse is checked daily against the live service.

Daily averagePeak 1166ms
Oct 3Today
Fastest day
712ms
Slowest day
1166ms
14-day trend
Stable-4%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of ClickHouse, so you can see the experience inside your AI.

It does not authenticate your account with ClickHouse. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

ClickHouse Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_567ij3B5hJvT6KRM8Z5LcFbGNttrwDvwD2OPp6c2/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — ClickHouse capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "clickhouse-vector-search-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_567ij3B5hJvT6KRM8Z5LcFbGNttrwDvwD2OPp6c2/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up ClickHouse in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work ClickHouse owners hand off.

This MCP is built for technical users who need to bridge the gap between analytical databases and AI agents.

  • 01

    Data Analysts

    They hand off the task of writing complex SQL queries to the agent to get instant reports.

  • 02

    AI Developers

    They use the agent to test and debug vector similarity searches without writing boilerplate code.

  • 03

    Database Administrators

    They use the agent to monitor table statistics and cluster versions across different environments.

FAQ

Questions ClickHouse owners ask.

  • 01

    Can I use this with self-hosted ClickHouse?

    Yes. You can connect to both ClickHouse Cloud and self-hosted clusters by providing the correct URL and credentials.

  • 02

    Which AI clients can I use with this MCP?

    You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Does this support vector similarity searches?

    Yes. The MCP includes a vector_search capability that uses mathematical distance traces for high-dimensional semantic search.

  • 04

    Can I run DDL commands through the agent?

    Yes. The execute_sql capability allows you to push DDL, DML, and SELECT queries to your cluster.

  • 05

    How does Vinkius handle my credentials?

    Vinkius hosts the MCP and manages your credentials so you can connect your client once and start working immediately.

  • 06

    Can my agent perform high-speed vector similarity searches?

    Yes. Provide the database, table, and the vector embedding array in JSON format. The agent uses ClickHouse's native distance functions (cosine or L2) to return the closest matches, leveraging ClickHouse's industry-leading OLAP performance.

  • 07

    Can I execute arbitrary SQL commands directly through the agent?

    Absolutely. The 'execute_sql' capability allows you to push any valid ClickHouse SQL (DML, DDL, or SELECT) to your cluster. This is perfect for managing tables, updating records, or generating custom analytical reports on the fly.

  • 08

    How do I check if my ClickHouse instance supports HNSW indices?

    Ask your agent to get the version details. The agent checks your ClickHouse build and identifies exactly which capability branches are active, confirming if advanced vector features like HNSW support are available in your runtime environment.

Explore

More in AI Frontier

Suggestions

Connect ClickHouse to Claude, Cursor, ChatGPT & more