How to Use the ClickHouse (Vector Search) MCP in Windsurf

Q: How does Windsurf use the ClickHouse (Vector Search) server to find data?

Windsurf's Cascade agent uses the vectorsearch tool from this MCP Server. You give it a high-level goal, and it automatically calls the tool with the right parameters to query your embeddings in ClickHouse.

Q: Can I run custom SQL on my database with this?

Yes. The executesql tool lets you run any SQL query directly from Windsurf. You can ask your agent to fetch data, update records, or even modify table structures.

Run vector searches and manage ClickHouse tables in Windsurf. Cascade, its autonomous agent, chains all the steps for you.

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 Windsurf

Create your Vinkius account to connect ClickHouse (Vector Search) to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find Anything with Vector Search

The `vector_search` tool connects Windsurf directly to your ClickHouse embeddings. Just tell Cascade to find similar records, and it figures out the rest. It can find semantically related documents, images, or any other data you've vectorized. This isn't just about running one query. Cascade chains actions. After using `vector_search` to get a list of IDs, it can then use `execute_sql` to fetch the full records for those IDs, all without you having to prompt it for the next step.

Manage Schemas from Your Editor

Stop switching to a separate database client just to remember a table name. Ask Windsurf to explore your database, and it will use the `list_databases` and `list_tables` tools to get a map of your instance. From there, it can dig deeper with `describe_table` to get column names and types. This means when you ask it to write code against your database, it already knows the schema and generates code that actually works.

Your ClickHouse MCP Server

This MCP Server gives Windsurf's Cascade agent direct, authenticated access to your database. The `execute_sql` tool is the main workhorse, letting your agent run any DML, DDL, or SELECT statement you need. Because Cascade can plan multi-step operations, it can use this to perform complex tasks. You could ask it to 'archive old user records,' and it could plan a sequence of `SELECT` and `DELETE` queries to get the job done safely.

Setup guide

Set up ClickHouse (Vector Search) MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my ClickHouse (Vector Search) payment history." If connected, Cascade will call the ClickHouse (Vector Search) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "clickhouse-vector-search-mcp": {
      "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 Windsurf

Windsurf's Cascade agent uses the `vector_search` tool from this MCP Server. You give it a high-level goal, and it automatically calls the tool with the right parameters to query your embeddings in ClickHouse.

Yes. The `execute_sql` tool lets you run any SQL query directly from Windsurf. You can ask your agent to fetch data, update records, or even modify table structures.

The key is Windsurf's autonomous agent, Cascade. It can chain multiple tools together. It might use `vector_search` to find IDs, then `execute_sql` to get the full records, all in one continuous operation without you guiding each step.

You can add it with one click from the built-in MCP Marketplace inside Windsurf. Alternatively, you can add the server URL manually in your `mcp_config.json` file or through the Settings UI.

Your SQL queries and vector data are processed in an ephemeral sandbox. Vinkius handles the authentication via your endpoint token, but the MCP server itself doesn't store your query history or results after the request is complete.

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