How to Use the MyScale (SQL Vector Database API) MCP in Windsurf

Q: How do I connect MyScale (SQL Vector Database API) to Windsurf?

Open your mcpconfig.json file in the /.codeium/windsurf directory. Add the server details under the mcpServers key, then click Refresh in the MCP panel.

Q: Can Windsurf run hybrid search queries with MyScale (SQL Vector Database API)?

Yes. Cascade can use executesqlquery to combine exact keyword matches with vector similarity. The database handles the heavy lifting while the agent parses the JSON results.

Q: Does the agent know when my vector index is ready?

It figures it out automatically. Cascade calls checkindexstatus and waits for the Built state before attempting to run any similarity searches.

Let Windsurf build and query your vector database. Cascade chains SQL operations directly against your cluster.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MyScale (SQL Vector Database API) MCP to Windsurf

Create your Vinkius account to connect MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Windsurf build your schemas

Cascade doesn't wait for you to run database migrations. When you ask for a new semantic search feature, it calls `ping_cluster` to verify connectivity. Then it immediately uses `create_vector_table` to set up the exact schema your application needs. You don't have to manually tune the indices either. The agent executes `create_vector_index` and loops `check_index_status` in the background until the state hits Built. You just watch the MCP Server handle the infrastructure while you focus on the application logic.

Run raw SQL through this MCP Server

Sometimes you need standard relational data, and sometimes you need vector similarity. Windsurf handles both through the same interface. It uses `execute_sql_query` to pull standard rows, automatically formatting the SELECT results as JSON so the agent can parse them instantly. For semantic matching, Cascade switches to `vector_search`. It builds the SQL query under the hood and returns the nearest neighbors. You get a hybrid database workflow without writing a single line of boilerplate driver code.

End-to-end vector pipelines

The real advantage here is how Cascade chains these operations. You tell it to ingest a folder of markdown files and make them searchable. It reads the files, generates the embeddings, inserts them via SQL, and verifies the index. If a query fails, the agent reads the error from the database and rewrites the statement. It handles the entire lifecycle of your vector data. Connecting this MCP integration means you stop context-switching between your editor and your database console.

Setup guide

Set up MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) payment history." If connected, Cascade will call the MyScale (SQL Vector Database API) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "myscale-sql-vector-database-api-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 MyScale. 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 MyScale (SQL Vector Database API) 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 MyScale (SQL Vector Database API) MCP in Windsurf

Open your mcp_config.json file in the ~/.codeium/windsurf directory. Add the server details under the mcpServers key, then click Refresh in the MCP panel.

Yes. Cascade can use execute_sql_query to combine exact keyword matches with vector similarity. The database handles the heavy lifting while the agent parses the JSON results.

It figures it out automatically. Cascade calls check_index_status and waits for the Built state before attempting to run any similarity searches.

Standard drivers require you to write and maintain connection logic. This native integration gives your agent direct access, letting it interact with your cluster via raw SQL.

This integration only touches the specific vector arrays, text strings, and table schemas you explicitly ask the agent to query. Your database credentials stay local to your machine, and the server strictly routes the SQL commands you authorize.

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