How to Use the pgvector (Vector Database) MCP in Cursor

Q: How does Cursor use pgvector (Vector Database) to run similarity searches?

In Agent mode, Cursor invokes the searchvectors tool to query your database. It returns real vector distance results directly into your active coding workspace.

Q: Can I view my database table structures directly inside the editor?

Yes. The listtables tool lets your agent read and display your current database tables, ensuring you write queries against actual columns.

Inject live semantic search results directly into your Cursor codebase using pgvector (Vector Database) tools.

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 Cursor

Create your Vinkius account to connect pgvector (Vector Database) to Cursor — 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Write code using real pgvector schemas

The `list_tables` tool gives your Cursor agent an immediate map of your existing PostgreSQL vector relations over this MCP link. When writing database queries, the Cursor editor reads these real pgvector schemas to generate accurate SQL instead of hallucinating table structures. Once the Cursor agent knows your tables, it calls `create_table` to build new vector columns directly from your codebase files. This integrates your pgvector schema migrations right into your active Cursor coding session.

Run live similarity queries inside Cursor Agent mode

The `search_vectors` tool executes real-time semantic lookups within Cursor to test your retrieval code against actual pgvector data. The Cursor agent pulls the exact matches and distances back into your editor so you can verify query logic instantly. You don't have to write dummy data generators when testing your Postgres database inside Cursor. By using the `insert_vector` tool, Cursor inserts real test embeddings directly into your database to validate your application's search behavior on the spot.

Manage indexes and vector pruning from your Cursor editor

The `create_index` tool configures HNSW or IVFFlat indexes on your pgvector columns directly through this Cursor MCP Server. Your Cursor agent analyzes your database table sizes and runs the index creation without forcing you to open a separate terminal. If your test cases write bad data, the `delete_vector` tool removes those specific vectors from Postgres immediately. This keeps your development database clean while you iterate on your embedding pipelines inside Cursor.

Setup guide

Set up pgvector (Vector Database) MCP in Cursor

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the pgvector (Vector Database) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent pgvector (Vector Database) transactions." If the MCP tools are loaded correctly, Cursor will call the pgvector (Vector Database) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

In Agent mode, Cursor invokes the `search_vectors` tool to query your database. It returns real vector distance results directly into your active coding workspace.

Yes. You can tell your Cursor agent to optimize your search performance, and it will execute `create_index` to build HNSW indexes on your tables.

You provide the raw embedding array to the Cursor agent, which runs the `insert_vector` tool to write the data directly to your table.

Yes. The `list_tables` tool lets your agent read and display your current database tables, ensuring you write queries against actual columns.

Every PostgreSQL connection string and vector array stays on your machine. Cursor talks directly to your local database port, meaning your production keys and search embeddings are never sent to a third-party cloud.

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