Does it work with Oracle Autonomous Database?

Yes. Oracle Autonomous Database on OCI has ORDS enabled by default. Use the ORDS URL from your ADB instance (e.g., https://xxxxx.adb.us-ashburn-1.oraclecloudapps.com/ords), your schema name (typically ADMIN), and the admin credentials. The VECTOR type is available on all 23ai-compatible instances.

Can I run arbitrary SQL — not just vector searches?

Yes. The execute_sql_query tool accepts any valid Oracle SQL statement and returns results through ORDS. Add FETCH FIRST N ROWS ONLY to keep payloads manageable. This makes the agent useful for relational queries too, not just vector operations.

Which distance metrics are available for vector search?

Oracle 23ai supports COSINE and EUCLIDEAN (L2) distance metrics natively via VECTOR_DISTANCE. Specify the metric when running a search — cosine is recommended for most text embedding use cases, while L2 works better for image or audio embeddings.

Oracle Vector DB MCP Server for OpenAI Agents SDK 7 tools — connect in under 2 minutes

Name: Oracle Vector DB
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 7 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Oracle Vector DB through 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="Oracle Vector DB Assistant",
            instructions=(
                "You help users interact with Oracle Vector DB. "
                "You have access to 7 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Oracle Vector DB"
        )
        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 Oracle Vector DB MCP Server

Bring your Oracle Database 23ai vector capabilities directly into your AI agent workflow. Run VECTOR_DISTANCE similarity searches, inspect table schemas, execute SQL queries, and manage vector indexes — all through natural conversation.

The OpenAI Agents SDK auto-discovers all 7 tools from Oracle Vector DB through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Oracle Vector DB, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Vector Similarity Search — Execute native Oracle 23ai VECTOR_DISTANCE queries with cosine or Euclidean metrics against any table with VECTOR columns
Schema Inspection — List all tables in your schema and describe column types, spotting VECTOR-enabled columns for embedding storage
SQL Execution — Run arbitrary SQL queries against Oracle via ORDS for ad-hoc analysis and data retrieval
Vector Index Management — List all HNSW and IVF vector indexes instantiated across your tables
Table Statistics — Get row counts and optimizer stats for capacity planning and query performance tuning
Version Check — Verify your Oracle runtime version to confirm 23ai vector feature compatibility

The Oracle Vector DB MCP Server exposes 7 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 Oracle Vector DB to OpenAI Agents SDK via MCP

Follow these steps to integrate the Oracle Vector DB 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 7 tools from Oracle Vector DB

Why Use OpenAI Agents SDK with the Oracle Vector DB MCP Server

OpenAI Agents SDK provides unique advantages when paired with Oracle Vector DB 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

Oracle Vector DB + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Oracle Vector DB MCP Server delivers measurable value.

Automated workflows: build agents that query Oracle Vector DB, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Oracle Vector DB, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Oracle Vector DB tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Oracle Vector DB to resolve tickets, look up records, and update statuses without human intervention

Oracle Vector DB MCP Tools for OpenAI Agents SDK (7)

These 7 tools become available when you connect Oracle Vector DB to OpenAI Agents SDK via MCP:

describe_table

Describe table columns and explicit data types including VECTORs

execute_sql_query

WARNING: Output payload size is inherently limited, restrict rows fetched (FETCH FIRST 100 ROWS ONLY) to ensure stability. Execute arbitrary SQL query against the Oracle runtime via ORDS

get_database_version

Get exact Oracle DB Runtime version banner

list_tables

List accessible tables in the current Oracle schema

list_vector_indexes

List specialized AI Vector search indexes (HNSW, IVF) instantiated

table_stats

Get table cardinality and optimizer statistics

vector_search

1, -0.4, 0.5]` against a strict `VECTOR` column natively inside Oracle DB, sorting and fetching the nearest neighbors. Execute Vector similarity search via Oracle 23ai native VECTOR_DISTANCE

Example Prompts for Oracle Vector DB in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Oracle Vector DB immediately.

"Show me all tables in my schema that have VECTOR columns."

"Find the 5 most similar documents to this embedding using cosine distance."

"What version of Oracle is running and does it support vectors?"

Troubleshooting Oracle Vector DB MCP Server with OpenAI Agents SDK

Common issues when connecting Oracle Vector DB 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.

Oracle Vector DB + OpenAI Agents SDK FAQ

Common questions about integrating Oracle Vector DB 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.