About eia-mcp-gridsense
eia-mcp-gridsense is an MCP server that provides US electricity grid data from the EIA API. It is intended for clients that need regional generation and demand figures, state price proxies, or power-sector emissions.
Key features
- 01Hourly generation by fuel source
- 02Hourly regional electricity demand
- 03Monthly state retail price proxy
- 04Annual state power-sector CO2 emissions
- 05EIA API key configuration
Use cases
- 01Review generation mix for a grid region
- 02Track hourly electricity demand
- 03Examine state price proxies or annual emissions
MCP support
The MCP server exposes tools for querying EIA electricity generation, demand, retail price proxies, and power-sector CO2 emissions. It requires an EIA API key.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
uvx eia-mcp-gridsenseEIA_API_KEYSecretYour EIA API key (register at https://www.eia.gov/opendata/register.php)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEeia-mcp-gridsense
An MCP server exposing US electricity grid data from the EIA API:
get_fuel_mix— hourly generation by fuel source for a grid regionget_electricity_demand— hourly demand for a grid regionget_wholesale_prices— monthly retail price proxy for a stateget_co2_emissions— annual CO2 emissions by state, electric power sector
Setup
Requires an EIA API key: https://www.eia.gov/opendata/register.php
Set it as an environment variable (or in a local .env file, never committed):
EIA_API_KEY=your-key-here
Usage with Claude Desktop
{
"mcpServers": {
"eia-mcp-gridsense": {
"command": "uvx",
"args": ["eia-mcp-gridsense"],
"env": {
"EIA_API_KEY": "your-key-here"
}
}
}
}
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.