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.

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.

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.

pgvector (Vector Database) MCP Server for OpenAI Agents SDK 6 tools — connect in under 2 minutes

Name: pgvector (Vector Database)
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 6 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect pgvector (Vector Database) through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="pgvector (Vector Database) Assistant",
            instructions=(
                "You help users interact with pgvector (Vector Database). "
                "You have access to 6 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from pgvector (Vector Database)"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About pgvector (Vector Database) MCP Server

Connect your PostgreSQL + pgvector database to any AI agent and manage vector embeddings, similarity searches, and index optimizations through natural conversation.

The OpenAI Agents SDK auto-discovers all 6 tools from pgvector (Vector Database) through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries pgvector (Vector Database), another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Vector Similarity Search — Run nearest-neighbor queries using cosine, L2, or inner product distance metrics across millions of embeddings with a single prompt.
Table Management — Discover which tables contain vector columns, create new embedding tables with custom dimensions, and inspect your schema.
Embedding CRUD — Insert, update, and delete individual vector entries with metadata, keeping your knowledge base fresh and accurate.
Index Optimization — Create HNSW or IVFFlat indexes on vector columns to accelerate approximate nearest-neighbor (ANN) queries by orders of magnitude.

The pgvector (Vector Database) MCP Server exposes 6 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect pgvector (Vector Database) to OpenAI Agents SDK via MCP

Follow these steps to integrate the pgvector (Vector Database) MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 6 tools from pgvector (Vector Database)

Why Use OpenAI Agents SDK with the pgvector (Vector Database) MCP Server

OpenAI Agents SDK provides unique advantages when paired with pgvector (Vector Database) through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

pgvector (Vector Database) + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the pgvector (Vector Database) MCP Server delivers measurable value.

Automated workflows: build agents that query pgvector (Vector Database), process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries pgvector (Vector Database), another analyzes results, a third generates reports

Data enrichment pipelines: stream data through pgvector (Vector Database) tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query pgvector (Vector Database) to resolve tickets, look up records, and update statuses without human intervention

pgvector (Vector Database) MCP Tools for OpenAI Agents SDK (6)

These 6 tools become available when you connect pgvector (Vector Database) to OpenAI Agents SDK via MCP:

create_index

Create vector index

create_table

Create vector table

delete_vector

Delete a vector

insert_vector

Insert a vector

list_tables

List tables

search_vectors

Vector similarity search

Example Prompts for pgvector (Vector Database) in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with pgvector (Vector Database) immediately.

"Show me all tables with vector columns in my database."

"Search for the 5 most similar documents to this query in the document_chunks table."

"Create a new table called 'support_tickets' with 1536-dimension vectors and an HNSW index."

Troubleshooting pgvector (Vector Database) MCP Server with OpenAI Agents SDK

Common issues when connecting pgvector (Vector Database) to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

pgvector (Vector Database) + OpenAI Agents SDK FAQ

Common questions about integrating pgvector (Vector Database) MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.