How to Use the EIA Petroleum — Oil Market Intelligence MCP in Pydantic AI

Q: Does EIA Petroleum — Oil Market Intelligence support runtime validation in Pydantic AI?

Yes, the framework parses the JSON outputs from tools like getpetroleumtrade directly into Pydantic models. This ensures your agent never processes malformed trade or import data.

Q: How do I fetch weekly supply and demand data?

Call getpetroleumsummary to retrieve the latest weekly status report. Your agent uses this data to balance domestic production against current consumption rates.

Run type-safe oil market analysis with Pydantic AI and get validated WTI, Brent, and production metrics at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EIA Petroleum — Oil Market Intelligence MCP to Pydantic AI

Create your Vinkius account to connect EIA Petroleum — Oil Market Intelligence to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup EIA Petroleum — Oil Market Intelligence with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate oil price data at runtime

The `get_petroleum_prices` tool fetches current spot prices for WTI, Brent, gasoline, and diesel. When using Pydantic AI, every price point returned by this tool is validated against strict Python type models before your agent processes it. If the underlying data format changes, the agent raises an immediate validation error instead of passing corrupt pricing to your trading models. This guarantees data integrity for production financial pipelines.

Run type-safe production tracking via MCP Server

The `get_crude_production` tool retrieves U.S. crude oil production and reserves metrics. Connecting this MCP Server to your Pydantic AI agent ensures that production volume fields are parsed as exact floats. This prevents silent failures where a missing field or malformed string could skew your domestic supply models. Your agent works with clean, structured data every time.

Monitor refinery operations without silent errors

The `get_refinery_operations` tool checks capacity, utilization, and processing metrics across active refineries. Pydantic AI enforces type safety on these utilization rates, ensuring they fall within expected percentage ranges. Your agent uses these validated metrics to calculate fuel yields. Because the framework is model-agnostic, you can switch LLMs behind the scenes while keeping your data validation rules intact.

Setup guide

Set up EIA Petroleum — Oil Market Intelligence 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": {
        "eia-petroleum-oil-market-intelligence-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to EIA Petroleum — Oil Market Intelligence tools.",
)

result = await agent.run("List recent EIA Petroleum — Oil Market Intelligence 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 EIA. 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 EIA Petroleum — Oil Market Intelligence 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 EIA Petroleum — Oil Market Intelligence MCP in Pydantic AI

Use the MCP Server integration via MCPToolset with your Vinkius HTTP endpoint and pass it to your Agent's toolsets list. This unified approach handles server communication and exposes tools like `get_petroleum_stocks` safely.

Yes, the framework parses the JSON outputs from tools like `get_petroleum_trade` directly into Pydantic models. This ensures your agent never processes malformed trade or import data.

Yes, this setup is completely model-agnostic. You can run local models or commercial APIs to process data from `get_petroleum_summary` while maintaining strict runtime validation.

Call `get_petroleum_summary` to retrieve the latest weekly status report. Your agent uses this data to balance domestic production against current consumption rates.

Your specific trade queries and refinery capacity parameters are isolated within a secure V8 sandbox. No data is stored, and all connections are terminated immediately after the tool execution finishes.

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