New England Power Grid MCP Server

New England Power Grid MCP Server

Provides AI models with real-time data about New England's power grid through a Model Context Protocol interface, enabling questions about current power generation, fuel mix, and marginal fuels.

Category
访问服务器

README

Model Context Protocol for ISO New England Energy Grid Information

This project implements a Model Context Protocal (MCP) Server for information on New Englands power grid. Data is sourced from ISO New England, which oversees the day-to-day operation of the New England Power Grid. This MCP server is built atop the ISO Express web services API from ISO New England, documented at [https://webservices.iso-ne.com/docs/v1.1/]

What is an MCP Server and Why Do We Need One

An MCP server is a standardized interface to provide "tools" for artificial intelligence models, in particular, large language models (LLMs). A canonical example is a question to an LLM like "what is the weather in San Fransciso right now?". An LLM can't answer that on its own. It needs a "tool" to be able to go and get the weather right now to answer that question

What do you need to use this MCP Server

You need to create a free ISO Express account with ISO New England to get a username and password

What questions can this MCP server answer

Example Question: What is the marginal fuel right now in new england? Example Answer: The marginal fuel is Natural Gas and Wood Internal Implementation: accesses the /genfuelmix/current api endpoint Note: The marginal fuel is the type of power that will be used if you wanted to use power on the grid right now, how would the grid provide that additional power

What is the base api for iso-ne

The base api for the iso-new webservices api is [https://webservices.iso-ne.com/api/v1.1]

Installation and Setup

1. Install Dependencies

pip install -r requirements.txt

2. Configure Credentials

  1. Copy the example environment file:

    cp .env.example .env
    
  2. Edit .env and add your ISO Express credentials:

    ISO_NE_USERNAME=your_actual_username
    ISO_NE_PASSWORD=your_actual_password
    

3. Test the Server

You can test the MCP tools directly:

python test_mcp_tools.py

Running the MCP Server

Option 1: Direct Execution

python run_mcp_server.py

Option 2: Using the main module

python main.py

The server will communicate via JSON-RPC over stdin/stdout and can be connected to MCP clients like Claude Desktop.

MCP Client Configuration

Claude Desktop Configuration

Add this to your Claude Desktop MCP configuration file:

{
  "mcpServers": {
    "iso-newengland": {
      "command": "python",
      "args": ["/path/to/your/iso_newengland_mcp_server/run_mcp_server.py"],
      "env": {
        "ISO_NE_USERNAME": "your_iso_ne_username",
        "ISO_NE_PASSWORD": "your_iso_ne_password"
      }
    }
  }
}

Replace /path/to/your/ with the actual path to your project directory.

Available Tools

get_marginal_fuel()

Returns the current marginal fuel types for the New England power grid. The marginal fuel is the type of power generation that would be used if additional power was needed on the grid right now.

Example Usage: "What is the marginal fuel right now in New England?"

Marginal Fuel Example

get_full_fuel_mix()

Returns the complete current generation fuel mix for the New England power grid, including generation amounts in megawatts and which fuels are marginal.

Example Usage: "Show me the complete fuel mix for New England's power grid right now."

Fuel Mix Example

Project Structure

iso_newengland_mcp_server/
├── main.py                 # Main entry point
├── run_mcp_server.py       # Convenience script with better error handling
├── test_mcp_tools.py       # Test script for MCP tools
├── test_api_direct.py      # Direct API testing script
├── requirements.txt        # Python dependencies
├── .env.example           # Example environment variables
├── mcp-config.json        # Example MCP client configuration
└── src/
    ├── __init__.py
    ├── server.py          # FastMCP server implementation
    ├── api/
    │   ├── __init__.py
    │   └── iso_ne_client.py   # ISO New England API client
    ├── config/
    │   ├── __init__.py
    │   └── settings.py        # Configuration management
    └── models/
        ├── __init__.py
        └── fuel_mix.py        # Pydantic data models

API Details

This MCP server uses the ISO New England Web Services API v1.1. The base URL is:

https://webservices.iso-ne.com/api/v1.1

Endpoints Used

  • /genfuelmix/current - Current generation fuel mix data

Full endpoint example to get a json result: [https://webservices.iso-ne.com/api/v1.1//genfuelmix/current.json]

Authentication

The API requires HTTP Basic Authentication over SSL using your ISO Express credentials.

Troubleshooting

Common Issues

  1. Missing Credentials Error

    • Make sure you've created a .env file with your ISO Express credentials
    • Verify your username and password are correct
  2. API Authentication Errors

    • Verify your ISO Express account is active
    • Check that your credentials are correctly set in the .env file
  3. Import Errors

    • Make sure all dependencies are installed: pip install -r requirements.txt
    • Verify you're running from the project root directory

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选