mcpcost

industries.cascade/ephemeris

Ephemeris Time-Series Forecasting

Probabilistic time-series forecasts from zero-shot foundation models: routed, single or ensembled.

timeout probed 2026-10-15

fetch failed | Connect Timeout Error (attempted address: ephemeris.cascade.industries:443, timeout: 10000ms) | UND_ERR_CONNECT_TIMEOUT
Endpoint
https://ephemeris.cascade.industries/api/mcp (streamable-http)
Host
ephemeris.cascade.industries
Repository
https://github.com/TensorLink-AI/ephemeris-mcp
Website
https://ephemeris.cascade.industries
Registry
active, updated 2026-10-06 · registry entry
Reachable
3 of the last 3 probes

History

We add a row when the result changes. A server with no change keeps its last row.

ProbedResultInitToolsClaudeo200k
2026-10-10 10:11alive1.6 s75.2k3.0k
2026-10-07 11:07alive529 ms42.2k1.3k
2026-10-06 10:56needs auth

Badge and feed

mcpcost: timeout

[![mcpcost](https://mcpcost.ulehla.dev/badge/industries.cascade/ephemeris.svg)](https://mcpcost.ulehla.dev/s/industries.cascade/ephemeris)

An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.