How to Use the ClickHouse (Vector Search) MCP in Claude Code

Q: How do I connect Claude Code to the ClickHouse (Vector Search) MCP server?

You run a single command in your terminal: claude mcp add --transport http clickhouse-vector-search -- . Once added, Claude Code can use all the server's tools.

Q: Is this only for vector search?

No. While vectorsearch is a key feature, the server also provides tools for full SQL execution (executesql), schema inspection (listtables), and health checks (gettablestats). It's a general-purpose ClickHouse connector for your agent.

Automate ClickHouse operations from your terminal. Pipe vector search results or run SQL in any shell script or CI/CD pipeline.

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 Claude Code

Create your Vinkius account to connect ClickHouse (Vector Search) to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scriptable Vector Search

The `vector_search` tool lets you find data by semantic similarity, right from the command line. You can run a search and pipe the resulting JSON to another process like `jq` for filtering or a script for further action. This is perfect for automation. You can set up a cron job that runs a nightly search for duplicate items in your product catalog and flags them for review, all without any manual oversight.

Headless Database Administration

This MCP server gives your scripts direct access to manage ClickHouse. Use `list_databases` and `list_tables` to check what's there, then run a migration or cleanup job with `execute_sql`. You can write a simple bash script that uses `get_table_stats` to monitor table sizes. If a table grows past a certain threshold, the script can trigger an archival process automatically.

Monitor Cluster Health from the CLI

Use Claude Code and this server to build simple, powerful monitoring tools. The `get_version` tool can be used in a script to confirm your cluster has the right features enabled, like HNSW support for vector search. Combine that with `get_table_stats` to pull internal health metrics. You can easily create a script that runs every five minutes, checks key stats, and sends a notification to a Slack webhook if something looks wrong.

Setup guide

Set up ClickHouse (Vector Search) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see clickhouse-vector-search-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest ClickHouse (Vector Search) transactions." It will automatically discover and invoke the available ClickHouse (Vector Search) tools.

Terminal

claude mcp add --transport http clickhouse-vector-search-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the ClickHouse (Vector Search) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "clickhouse-vector-search-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

You can call Claude Code from your pipeline script to execute a vector search using the `vector_search` tool. Then you can pipe the JSON output to another command to verify search results or check for data consistency after a deployment.

You can automate almost any database task. Write shell scripts for data migrations (`execute_sql`), nightly data quality checks (`vector_search`), or cluster health monitoring (`get_table_stats`, `get_version`).

You run a single command in your terminal: `claude mcp add --transport http clickhouse-vector-search -- `. Once added, Claude Code can use all the server's tools.

No. While `vector_search` is a key feature, the server also provides tools for full SQL execution (`execute_sql`), schema inspection (`list_tables`), and health checks (`get_table_stats`). It's a general-purpose ClickHouse connector for your agent.

The server processes the SQL commands and vector data you send from the CLI. It operates in a zero-trust environment where each request is authenticated via your token and runs in an isolated sandbox. Your query contents are not stored or logged.

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