How to Use the ISO New England MCP in Pydantic AI

Q: Does Pydantic AI validate the ISO New England fuel mix data?

Yes, every response from getfuelmix is parsed against strict Pydantic models at runtime. Your Pydantic AI agent will raise a validation error if any fuel type or percentage field is missing or corrupted.

Q: Can I track regional power exchanges with ISO New England and Pydantic AI?

Yes, your agent uses getactualinterchange to check net imports and exports. Pydantic AI ensures that interchange values are correctly typed as floats before your agent runs calculations.

Q: What happens if a pricing query fails or returns empty data?

If getdayaheadlmp returns unexpected nulls, the framework raises a validation error. This prevents your agent from making decisions based on incomplete pricing structures.

Get type-safe ISO New England market data validated at runtime by your Pydantic AI agents for error-free grid automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ISO New England MCP to Pydantic AI

Create your Vinkius account to connect ISO New England 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 ISO New England with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate power prices at runtime with Pydantic AI

`get_lmp` fetches 5-minute locational marginal prices in USD/MWh and enforces strict type-safety on the response. Your Pydantic AI agent validates these price structures at runtime, ensuring your trading scripts never execute on malformed data. You can also use `get_hourly_lmp` to gather historical pricing trends safely. If the API schema changes, your Pydantic AI code fails immediately and loudly, preventing silent errors in your financial models.

Monitor grid stress using this MCP Server

`get_system_load` returns the real-time load in megawatts to track grid stress. This MCP Server ensures that the incoming megawatt integers match your expected Pydantic models before your agent evaluates grid stability. To look ahead, your agent calls `get_seven_day_forecast` to get load projections. This lets your type-safe agent plan power procurement without risking type errors during critical decision loops.

Track reserve margins and fuel metrics

`get_reserve` pulls the grid reserve requirements and clearing prices directly into your type-safe environment. Your Pydantic AI agent checks these margins to make sure there is enough backup capacity before recommending asset dispatch. The agent pairs this with `get_fuel_mix` to audit the real-time energy sources. It guarantees that the fuel percentages always parse into valid floats, keeping your environmental compliance reports accurate.

Setup guide

Set up ISO New England 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": {
        "iso-new-england-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent ISO New England 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 ISO New England. 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 ISO New England 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 ISO New England MCP in Pydantic AI

You instantiate the MCPToolset with your Vinkius HTTP endpoint URL. Pass this toolset directly into the toolsets parameter of your Pydantic AI Agent to expose all ten grid tools.

Yes, every response from `get_fuel_mix` is parsed against strict Pydantic models at runtime. Your Pydantic AI agent will raise a validation error if any fuel type or percentage field is missing or corrupted.

Yes, your agent uses `get_actual_interchange` to check net imports and exports. Pydantic AI ensures that interchange values are correctly typed as floats before your agent runs calculations.

If `get_day_ahead_lmp` returns unexpected nulls, the framework raises a validation error. This prevents your agent from making decisions based on incomplete pricing structures.

All requests for grid capacity and reserve data are routed through a zero-trust proxy on Vinkius. We never log the payloads of your queries, keeping your operational strategy and infrastructure checks entirely confidential.

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