Public energy data for your AI

Ask about the US grid.
Keep the evidence.

Connect an AI client to InfraMap's energy infrastructure data, with the same reach as the InfraMap PRO analyst. Screen the whole US plant inventory, then retrieve generation, ownership, emissions, price nodes, market prices, modeled curtailment and source records with citations and coverage gaps.

No account or API key required. The server is read-only. Connect using Streamable HTTP.

Connect

Open your AI client's MCP settings, add a remote server named inframap, and paste the endpoint above. For clients that accept JSON configuration, use:

{
  "mcpServers": {
    "inframap": {
      "url": "https://mcp.inframap.pro/mcp"
    }
  }
}

Remote MCP support depends on your client and its plan. This service supplies data and calculations. Your AI client writes the answer.

Questions to try

• Find the largest operating wind projects in Texas and show their exact project IDs.
• How many PJM plants have no market price node, and what are the documented reasons?
• Which wind and solar plants saw the largest increase in modeled curtailment from 2024 to 2025?
• Show Barry's reported generation in 2024, including missing months and source citations.
• What was Moccasin's day-ahead basis to its hub in June 2025?
• Which datasets can help me research cooling water use, and what do their records mean?

What the data can tell you

Each dataset has its own reporting period and coverage. Missing values stay missing. Modeled generation potential differs from delivered generation, and modeled curtailment is an experimental estimate, not operator-reported curtailment. Ownership conclusions retain their evidence dates. Every plant in the seven ISO and RTO markets has a reviewed price-node outcome, but a node association does not prove historical settlement, a contract or a physical connection.

Project IDs can group several EIA plants. Use the source coverage tool to resolve native IDs before joining source records. The service covers InfraMap's reviewed energy datasets. The separate data-center atlas and retained third-party research are not included.