← Browse
ephemeris
TensorLink-AI ★ 0
Ephemeris is an MCP server that forecasts numeric time series (sales, demand, traffic, load, prices, metrics) using six open-weight foundation models—Chronos-2, TimesFM 2.5, Toto 2, TiRex-2, PatchTST-FM r2, and FlowState r1—individually or as an accuracy-weighted ensemble. Claude Code users install the plugin to gain forecasting skills and one-call access to the remote API; it requires no training, feature engineering, or local GPU.
Install
> /plugin marketplace add TensorLink-AI/ephemeris-mcp
> /plugin install ephemeris
What it's made of
1 skill · 1 MCP server
- Commands
- 0
- Agents
- 0
- Skills
- 1
- MCP servers
- 1
- Hooks
- 0
What it needs & plugs into
- API keys
- none
- Paid services
- Ephemeris
- External tools
- none
- Talks to
ephemeris.cascade.industries
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (TensorLink-AI).