How to Use the Oracle Vector DB MCP in VS Code Copilot

Q: Can VS Code Copilot run live queries against Oracle Vector DB?

Yes, the executesqlquery tool allows Copilot to run live SQL queries. Ensure your developers use FETCH FIRST 100 ROWS ONLY to keep payload sizes within VS Code's processing limits.

Q: How does VS Code Copilot perform semantic search on Oracle Vector DB?

Copilot calls the native vectorsearch tool, which executes VECTORDISTANCE queries inside Oracle 23ai. This MCP Server executes the query and returns formatted results directly into the chat interface for immediate analysis.

Q: What version of Oracle DB does this extension support?

It requires Oracle Database 23ai. The getdatabaseversion tool allows Copilot to verify that your database supports the native vector operations required for semantic search.

Share Oracle 23ai vector search capabilities across your team using VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect Oracle Vector DB to VS Code Copilot — 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run vector searches inside VS Code Copilot

The `vector_search` tool executes native VECTOR_DISTANCE queries in Oracle 23ai to return semantic matches directly inside your Copilot chat. This allows your team to test database queries without leaving the IDE workspace. Your agent formats and displays the nearest-neighbor results in real time. Because the server runs on managed Vinkius infrastructure, every developer on your team uses the same secure endpoint connection.

Share database schemas with your team

The `describe_table` tool exposes Oracle 23ai table structures and vector columns directly to your VS Code Copilot environment. By committing a shared configuration to your repository, your entire team gets identical schema-awareness. The agent uses `list_tables` and `table_stats` to verify database structure before generating code. This shared context ensures that every developer writes queries that match the production database schema.

Verify indexes using this MCP Server

The `list_vector_indexes` tool retrieves the status of HNSW and IVF indexes directly into the VS Code chat interface. This helps your team verify that production indexes are active before deploying new search features. This MCP Server allows you to run test queries using the `execute_sql_query` tool to check index performance. Always include FETCH FIRST 100 ROWS ONLY in your team's test queries to keep the VS Code interface responsive.

Setup guide

Set up Oracle Vector DB MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Oracle Vector DB MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Oracle Vector DB tools listed. Try asking: "List my recent Oracle Vector DB transactions" and Copilot will invoke them automatically.

.vscode/mcp.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 VS Code Copilot

Create a .vscode/mcp.json file in your repository and commit it. Every team member with VS Code 1.96+ and Copilot Chat will automatically gain access to the database tools defined in the mcpServers configuration.

Yes, the `execute_sql_query` tool allows Copilot to run live SQL queries. Ensure your developers use FETCH FIRST 100 ROWS ONLY to keep payload sizes within VS Code's processing limits.

Copilot calls the native `vector_search` tool, which executes VECTOR_DISTANCE queries inside Oracle 23ai. This MCP Server executes the query and returns formatted results directly into the chat interface for immediate analysis.

It requires Oracle Database 23ai. The `get_database_version` tool allows Copilot to verify that your database supports the native vector operations required for semantic search.

Vinkius utilizes single-token authentication to manage connections within a secure, ephemeral sandbox. This MCP setup ensures your database credentials and raw table schemas are never exposed to the public internet or stored on external servers.

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