Ephemeris Time-Series Forecasting

Connect it to your AI

Claude Code

claude mcp add --transport http ephemeris https://ephemeris.cascade.industries/api/mcp

Claude, ChatGPT, Cursor and other apps

Add it as a custom connector with this URL (Streamable HTTP):

https://ephemeris.cascade.industries/api/mcp

This server expects extra headers, usually an API key from its maker.

claude mcp add ephemeris -e EPHEMERIS_API_KEY=… -- npx -y ephemeris-mcp@1.0.0

Cursor, VS Code and other apps (mcp.json)

{
  "mcpServers": {
    "ephemeris": {
      "url": "https://ephemeris.cascade.industries/api/mcp"
    }
  }
}

Tools it offers

7 tools, as the server itself reported during our check on Oct 31, 2026.

• get_versionRead this deployed MCP server's version, nullable build commit and supported saved forecast schema versions. Call with {}. No API key, account access, inference, charges or writes; network access to this server only. Ret
• describe_forecastDeterministic calculations from a complete ephemeris.forecast v1 artifact object, including CLI artifacts. No inference or forecast charge; this hosted tool still receives data over the network. Returns scope, result, ba
• plot_forecastRender a complete ephemeris.forecast v1 artifact object as PNG (default inline preview) or SVG (embedded resource to save). No inference or forecast charge; hosted processing receives the artifact over the network. Examp
• forecastSubmit numeric observations to forecast future sampling steps. Spends credits on successful calls. Choose and retain idempotency_key before submitting; no automatic retries, replay depends on server retention. Minimal ex
• list_modelsDiscover the model panel: each model's availability right now (healthy), capabilities (multivariate, covariates, max_horizon, auto_max_horizon), its weight in an ensemble at each horizon, pinned and actually served weigh
• get_balanceReturn the account's spendable credit balance in millicredits, excluding credits reserved by in-progress forecasts. 1000 millicredits equal one credit.
• get_usageReturn the account's forecast request log, newest first, with the mode, models used, series count, horizon, credits estimated and settled, HTTP status and latency of each request.

Questions