How to Use the ISO New England MCP in CrewAI

Q: Can a CrewAI team coordinate using both ISO New England pricing and load data?

Yes. You can assign getsystemload to a monitoring agent and getlmp to a pricing agent. They will collaborate, sharing their tool outputs to determine if high load is driving up regional energy costs.

Q: How do I limit which tools a specific agent can access?

Use the MCPServerHTTP class from crewai.mcp and apply a toolfilter. This lets you restrict access, ensuring your pricing agent only sees LMP tools while your operations agent handles load metrics.

Deploy specialized CrewAI agent teams to autonomously analyze ISO New England fuel mix, pricing spikes, and grid load.

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 CrewAI

Create your Vinkius account to connect ISO New England to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent grid analysis

This MCP Server exposes live generation sources and electricity demand through `get_fuel_mix` and `get_system_load`. With CrewAI, you don't just ask one agent to look at this data. You set up a team where one agent monitors the fuel mix while another analyzes the load. They share a common memory space to coordinate their findings. If the fuel mix agent notices natural gas generation dropping, it alerts the load agent to check if prices are spiking. This cooperative approach gives you deep insights without manual scripting.

Track market volatility with CrewAI

Your CrewAI analyst agent tracks market volatility using `get_day_ahead_lmp` and `get_hourly_lmp`. It works alongside a moderator agent that watches for extreme pricing anomalies. Together, they can flag abnormal day-ahead clearing prices before the trading day starts. The agents execute sequentially, passing their findings down the line. The analyst fetches the numbers, writes a quick summary, and hands it off to the reporter agent to write a daily digest.

Track regional transmission with this MCP Server

The ISO New England MCP Server feeds regional transmission and historical load data to your agents via `get_actual_interchange` and `get_hourly_load`. Your crew uses this to map how much power is imported from Canada or New York during peak stress hours. By assigning this tool to a specialized transmission agent, you isolate the task of monitoring border flows. The agent can run in the background, updating its shared memory so other agents always have the latest transmission context.

Setup guide

Set up ISO New England MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke ISO New England tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="ISO New England Analyst",
    goal="Access and analyze ISO New England data via MCP.",
    backstory="Expert analyst with direct ISO New England access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent ISO New England transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="ISO New England Analyst",
        goal="Access and analyze ISO New England data via MCP.",
        backstory="Expert analyst with direct ISO New England access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent ISO New England transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass your Vinkius server HTTP URL directly into the agent's `mcps` parameter during initialization. CrewAI automatically discovers the tools and makes them available for the agent to use during its tasks.

Yes. You can assign `get_system_load` to a monitoring agent and `get_lmp` to a pricing agent. They will collaborate, sharing their tool outputs to determine if high load is driving up regional energy costs.

It does. You can set up a manager agent that decides when to call specific tools like `get_fuel_mix` or `get_reserve`. The manager delegates these tasks to subordinate agents based on the current grid situation.

Use the `MCPServerHTTP` class from `crewai.mcp` and apply a `tool_filter`. This lets you restrict access, ensuring your pricing agent only sees LMP tools while your operations agent handles load metrics.

Yes. The server only fetches public ISO New England grid and energy market data, such as fuel mix percentages and system loads. All communication goes through Vinkius's secure sandbox, meaning your internal agent prompts and API keys remain completely isolated.

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