How to Use the pgvector (Vector Database) MCP in VS Code Copilot

Q: Can I manage my vector tables using pgvector (Vector Database) inside VS Code Copilot?

Yes. Your agent can run createtable to create new columns and listtables to inspect existing schemas directly from your workspace.

Q: How does pgvector (Vector Database) optimize searches inside VS Code Copilot?

The agent invokes the createindex tool to build HNSW indexes on your vector columns, ensuring your semantic searches remain fast as your database scales.

Q: Can I delete individual embeddings from my database using the chat?

Yes. The deletevector tool allows you to purge specific vector records directly from your database using their unique identifiers.

Share database tools across your engineering team with the pgvector (Vector Database) MCP Server for 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 pgvector (Vector Database) MCP to VS Code Copilot

Create your Vinkius account to connect pgvector (Vector Database) 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 pgvector (Vector Database) with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-wide schema management in VS Code Copilot

The `list_tables` tool inspects your PostgreSQL instance and shares the exact vector schema with VS Code Copilot over this MCP connection. This ensures every developer on your team writes queries against the correct, live pgvector tables instead of guessing column names inside VS Code Copilot. When schemas need to change, your team uses `create_table` to build vector columns with matching dimensions directly from VS Code Copilot. It keeps Postgres setups consistent across different development environments without manual SQL scripts.

Direct vector testing inside your workspace

The `insert_vector` tool lets VS Code Copilot write test embeddings straight into your Postgres database tables. Developers can verify how their application handles high-dimensional vectors by writing real records directly from the VS Code Copilot chat interface. If a test goes sideways, the `delete_vector` tool removes those specific rows from your pgvector database. This ensures your shared development database doesn't get cluttered with junk embeddings during active testing phases inside VS Code Copilot.

Run semantic lookups from VS Code Copilot

The `search_vectors` tool triggers similarity searches inside your PostgreSQL database directly from your VS Code Copilot chat. It pulls the closest matching pgvector records using native distance operators, bringing real database context straight into your workspace. To keep queries fast, the `create_index` tool builds HNSW or IVFFlat indexes on your vector columns. VS Code Copilot runs this index creation through the MCP Server, keeping your pgvector database optimized without manual DBA intervention.

Setup guide

Set up pgvector (Vector Database) 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 pgvector (Vector Database) 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 pgvector (Vector Database) tools listed. Try asking: "List my recent pgvector (Vector Database) transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "pgvector-vector-database-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 pgvector. 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 pgvector (Vector Database) 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 pgvector (Vector Database) MCP in VS Code Copilot

You ask Copilot Chat to find matching data. The agent runs the `search_vectors` tool against your database and displays the closest records in your editor pane.

Yes. Your agent can run `create_table` to create new columns and `list_tables` to inspect existing schemas directly from your workspace.

The agent invokes the `create_index` tool to build HNSW indexes on your vector columns, ensuring your semantic searches remain fast as your database scales.

Yes. The `delete_vector` tool allows you to purge specific vector records directly from your database using their unique identifiers.

Your PostgreSQL connection strings and vector embeddings are processed locally. VS Code Copilot routes these requests through your secured local MCP Server configuration, keeping your credentials completely isolated from 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