How to Use the Oracle Vector DB MCP in Pydantic AI

Q: How do I connect Pydantic AI to the Oracle Vector DB MCP Server?

You instantiate the MCPToolset with your Vinkius HTTP endpoint and pass it to the toolsets argument of your Pydantic AI Agent.

Q: How does Pydantic AI validate vector search results from Oracle Vector DB?

The framework intercepts the JSON output of the vectorsearch tool and validates the float arrays and distance metrics against its built-in Python schemas.

Q: Can I check the database version before running vector queries?

Yes, the agent calls getdatabaseversion to verify that the runtime is indeed Oracle 23ai, ensuring compatibility with native vector operations.

Query your Oracle 23ai database with strict runtime validation using Pydantic AI and native vector search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Oracle Vector DB MCP to Pydantic AI

Create your Vinkius account to connect Oracle Vector DB to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Oracle Vector DB with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Vector Searches

The `vector_search` tool executes native vector distance queries directly inside Oracle 23ai and returns structured results. Because Pydantic AI validates every incoming payload, your agent receives strictly typed coordinate and distance data without risking silent data corruption. This MCP Server ensures that the float arrays returned by your semantic searches perfectly match your Python models. If the database returns unexpected formats, the toolset raises a validation error immediately rather than passing bad data to your LLM.

Schema Validation and Index Discovery via MCP Server

The `describe_table` tool inspects database columns and explicit vector types to build a strict runtime schema map. Your Pydantic AI agent uses this data to verify that its SQL queries align with the actual database structure before sending them. The agent also calls `list_vector_indexes` to check for active HNSW or IVF indexes. This guarantees that your agent only attempts vector operations on columns that actually support native similarity search, avoiding database runtime errors.

Controlled SQL Execution

The `execute_sql_query` tool runs raw SQL queries against your Oracle database runtime via ORDS when standard vector tools are not enough. The tool caps results with a strict FETCH FIRST 100 ROWS ONLY limit to prevent massive payloads from failing validation. Your agent can check `table_stats` to verify table cardinality and optimizer statistics before running these raw queries. This step keeps your database queries highly optimized and prevents Pydantic AI from processing massive, unparsed datasets.

Setup guide

Set up Oracle Vector DB MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "oracle-vector-db-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Oracle Vector DB tools.",
)

result = await agent.run("List recent Oracle Vector DB transactions")
print(result.output)

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 Oracle Database. 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 Oracle Vector DB 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 Oracle Vector DB MCP in Pydantic AI

You instantiate the `MCPToolset` with your Vinkius HTTP endpoint and pass it to the `toolsets` argument of your Pydantic AI `Agent`.

The framework intercepts the JSON output of the `vector_search` tool and validates the float arrays and distance metrics against its built-in Python schemas.

The framework will raise a validation error instantly. This prevents the agent from making decisions based on broken database payloads or corrupted schema data.

Yes, the agent calls `get_database_version` to verify that the runtime is indeed Oracle 23ai, ensuring compatibility with native vector operations.

Yes, the MCP host manages your database credentials within an ephemeral, zero-trust V8 sandbox. The connection details never leak into your Python runtime or LLM context.

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