English Français العربية

io.github.kardashev-lab/kardashev-mcp

Official registry AI and agents

US grid data for agents: LMP, carbon, load, queues, ERCOT large loads, RT−DA spread forecasts.

Source code Website Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package kardashev-mcp
Claude Code 
claude mcp add kardashev-mcp -- npx -y kardashev-mcp@0.1.0
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "kardashev-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "kardashev-mcp@0.1.0"
            ]
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. kardashev-mcp
  2. Install
  3. Tools
  4. Optional env
  5. Develop
  6. Links
  7. License

kardashev-mcp

MCP server for Kardashev Labs US grid data. Gives agents live LMP, carbon intensity, load, curtailment, interconnection queues, ERCOT large loads, and the public RT−DA spread forecast track record. No API key required.

Data comes from the public API at data.kardashevlabs.org.

Install

npx -y kardashev-mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "kardashev": {
      "command": "npx",
      "args": ["-y", "kardashev-mcp"]
    }
  }
}
Claude Code
claude mcp add kardashev -- npx -y kardashev-mcp

Tools

ToolWhat it returns
list_isosCovered ISOs/RTOs and live ingest status
get_fuel_mixGeneration by fuel type (MW)
get_carbonCarbon intensity (lbs CO₂/MWh)
get_lmpLocational marginal prices (RT/DA)
get_loadActual grid load (MW)
get_load_forecastNear-term load forecast
get_curtailmentSolar/wind curtailment
get_queueInterconnection queue projects
get_large_loadERCOT large-load interconnection snapshot
get_spread_forecastLive ERCOT RT−DA spread forecast (issued before delivery)
get_forecast_track_recordScored public track record for the spread models

Row-returning tools default to limit=50 (hard max 500) so agents stay within context budgets.

Optional env

VariableDefaultPurpose
KARDASHEV_BASE_URLhttps://data.kardashevlabs.orgOverride API base (local data plane)
KARDASHEV_TIMEOUT_MS30000Per-request timeout

Develop

npm install
npm run build
npm start                 # stdio
npm run inspect           # MCP Inspector

License

MIT

Frequently asked questions

What is io.github.kardashev-lab/kardashev-mcp?

US grid data for agents: LMP, carbon, load, queues, ERCOT large loads, RT−DA spread forecasts.

How do I install io.github.kardashev-lab/kardashev-mcp?

It runs on your machine. In Claude Code: claude mcp add kardashev-mcp -- npx -y kardashev-mcp@0.1.0. For other clients, paste the JSON configuration from this page into their MCP settings.

Does io.github.kardashev-lab/kardashev-mcp need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is io.github.kardashev-lab/kardashev-mcp open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains io.github.kardashev-lab/kardashev-mcp?

It is published by kardashev-lab. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.