How to Use the Oracle Vector DB MCP in Windsurf

Q: Can Windsurf run raw SQL queries on Oracle Vector DB?

Yes, Cascade uses executesqlquery to run arbitrary SQL when needed. It automatically appends row limits to prevent massive data transfers from slowing down your IDE.

Q: How does Windsurf handle HNSW and IVF indexes in Oracle Vector DB?

Windsurf uses the listvectorindexes tool to inspect existing vector indexes. This lets Cascade determine if your vector searches are running on optimized indexes or raw tables.

Let Windsurf autonomously run native vector similarity searches and inspect your Oracle 23ai schemas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Oracle Vector DB MCP to Windsurf

Create your Vinkius account to connect Oracle Vector DB to Windsurf — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Oracle Vector DB with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Oracle Vector DB searches directly in Windsurf

This MCP Server lets Windsurf execute vector similarity searches natively using the `vector_search` tool. Instead of manually writing complex SQL queries, you just tell Cascade what you need, and it queries vector embeddings using Oracle's native distance calculations. Cascade chains this search with other tools to analyze the results immediately. It pulls the raw vector distance scores, matches them against your dataset, and presents the nearest neighbors without requiring you to write a single line of database code.

Autonomous schema discovery and structural analysis

Cascade doesn't guess how your database is structured. It uses `list_tables` and `describe_table` to map out the exact columns, data types, and vector dimensions present in your Oracle schema tools exposed by the MCP Server. When you ask Cascade to build a feature, it inspects these tables to understand what data is available. It retrieves database properties using `get_database_version` to ensure compatibility with 23ai features before running queries.

Performance monitoring and index validation

Cascade monitors your database performance by using `list_vector_indexes` to check active indexes and `table_stats` to view optimizer statistics. If a query runs slow, Cascade can run `execute_sql_query` to check the execution plan, though it automatically appends limit clauses to keep payloads small. This keeps your development loop fast and prevents your database from stalling.

Setup guide

Set up Oracle Vector DB 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 Oracle Vector DB 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 Oracle Vector DB payment history." If connected, Cascade will call the Oracle Vector DB tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "oracle-vector-db-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 Oracle Database. 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 Oracle Vector DB 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 Oracle Vector DB MCP in Windsurf

You configure the MCP server in your local Windsurf settings file. Once connected, Cascade automatically discovers the schema tools and starts querying your Oracle 23ai instance directly.

Yes, Cascade uses `execute_sql_query` to run arbitrary SQL when needed. It automatically appends row limits to prevent massive data transfers from slowing down your IDE.

Windsurf uses the `list_vector_indexes` tool to inspect existing vector indexes. This lets Cascade determine if your vector searches are running on optimized indexes or raw tables.

No, the MCP tool handles the underlying Oracle 23ai native distance calculations for you. Cascade simply feeds the query array and gets back the sorted nearest neighbors.

Your database credentials and raw vector embeddings are processed within Vinkius's secure, isolated container. Windsurf only receives the final query results, meaning your production connection strings never leak to the AI client or external networks.

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