Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use pgvector with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Run vector similarity searches, manage embedding tables, and build AI-powered retrieval pipelines. all directly inside your existing PostgreSQL database.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 6 capabilities

The complete pgvector capability set.

These are the exact actions your AI can choose when you ask it to work with pgvector.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through pgvector.

  1. 01

    Create index

    Create vector index

  2. 02

    Create table

    Create vector table

  3. 03

    List tables

    List tables

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through pgvector.

  1. 04

    Search vectors

    Vector similarity search

  2. 05

    Insert vector

    Insert a vector

  3. 06

    Delete vector

    Delete a vector

Observed, not estimated

825ms average. Fast in production.

pgvector is checked daily against the live service.

Daily averagePeak 1044ms
Aug 20Today
Fastest day
685ms
Slowest day
1044ms
14-day trend
Slowing+8%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of pgvector, so you can see the experience inside your AI.

It does not authenticate your account with pgvector. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

pgvector Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_m3Dmr7TKd7NjkaPwx4OA0eTWiY7yo9GZdmp9NSJ4/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — pgvector capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "pgvector-vector-database-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_m3Dmr7TKd7NjkaPwx4OA0eTWiY7yo9GZdmp9NSJ4/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions pgvector owners ask.

  • 01

    Does the agent connect directly to my database?

    Yes. Your connection string is encrypted at rest and injected into an isolated runtime. The agent connects directly to your PostgreSQL instance. no intermediate proxies, no data copies, no third-party storage.

  • 02

    What vector dimensions are supported?

    Any dimension supported by pgvector. from small 128-d vectors to large 3072-d embeddings (e.g., OpenAI text-embedding-3-large). Specify the dimension when creating a table and the agent handles the rest.

  • 03

    Which distance metrics can I use for similarity search?

    pgvector supports three operators: ` (L2/Euclidean distance), (cosine distance), and ` (negative inner product). The agent uses cosine distance by default, which works best for normalized embeddings like those from OpenAI.

Explore

More in Loved By Devs

Suggestions