Ephemeris Time-Series Forecasting
Probabilistic time-series forecasts from zero-shot foundation models: routed, single or ensembled
What you can do with it
Share of each task's required capabilities it coversPrefer a ready-made agent?
An MCP server is a connector for your own assistant. These finished products do the job for you: build financial models.Similar tools
Listed for the same task: build financial modelsReviews
No review yet. Used Ephemeris Time-Series Forecasting? Be the first to help others choose.What it does
Ephemeris Time-Series Forecasting is an MCP server, a connector that lets an AI assistant use it as a tool. It can be used hosted (nothing to install) or installed locally.
From the publisher's description, Electra Index matched it to one capability: forecasting. That makes it a candidate for tasks such as build financial models or forecast demand.
Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.
At a glance
How to connect
As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 1d ago (live check)Hosted endpoint
https://ephemeris.cascade.industries/api/mcpstreamable-http
Install package
- NPM
ephemeris-mcpv1.0.0 · runs locally (stdio)
Required: Authorization, EPHEMERIS_API_KEY (get them from the publisher)
MCP settings (Claude Desktop, Cursor and other MCP clients)
{
"mcpServers": {
"ephemeris": {
"url": "https://ephemeris.cascade.industries/api/mcp",
"headers": {
"Authorization": "<your Authorization>"
}
}
}
}Replace the values in <angle brackets>.
Reliability
Re-tested about every 3 days · last check 1d agoObserved endpoint availability: the share of our conclusive checks that got an answer. A request for a key or sign-in counts as an answer (the server is up, its access is protected). Timeouts, unreachable endpoints, server errors and invalid MCP replies count as failures; rate-limited checks and checks during our own incidents are not counted. This is what we observed at each check, not continuous uptime: an outage between two checks may go unseen. The 90-day figure will appear once 90 days of checks exist (checks since 20 Oct 2026). How we measure
Tool changes
Tool tracking since 13 Nov 2026 · test history since 20 Oct 2026No tool added or removed since tracking started. 7 tools in the latest list.
Changes are confirmed by comparing complete tool lists only, read about every 3 days, and dated by the day we saw them. A renamed tool appears as one removal and one addition.
Live check
Electra Index connected to the hosted endpoint 1d agoONLINE Ephemeris Time-Series Forecasting answered an MCP connection on 19 Nov 2026 and introduced itself as ephemeris 1.2.1 (MCP protocol 2025-06-18).
7 tools offered to AI assistants
get_version· Read 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. Returns component, versdescribe_forecast· Deterministic 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, basis, limitations andplot_forecast· Render 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. Example: {artifact: <saveforecast· Submit 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 example: {mode: route,list_models· Discover 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 weight revision, price inget_balance· Return the account's spendable credit balance in millicredits, excluding credits reserved by in-progress forecasts. 1000 millicredits equal one credit.get_usage· Return 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.
What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Re-tested about every 3 days. Method
Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.
Facts & evidence
Each fact shows where it was seen and when.| Fact | Value | Evidence | Source | Last confirmed |
|---|---|---|---|---|
| Install package | ephemeris-mcp | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Hosted endpoint | https://ephemeris.cascade.industries/api/mcp | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Version | 1.0.1 | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Package registries | npm | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Local install (package) | yes | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Remote access (hosted) | yes | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Website | https://ephemeris.cascade.industries | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Repository | https://github.com/TensorLink-AI/ephemeris-mcp | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| Registry status | active | DECLARED | SRC-001 Official MCP Registry | 5d ago |
| MCP server | yes | DECLARED | SRC-001 Official MCP Registry | 5d ago |
Change history
- VERSION06 Oct 20261.0.0 → 1.0.1
- NEW06 Oct 2026first seen in the index
Is this page accurate?
Flag it and our robot re-checks the official source. Reports never change a score.Is Ephemeris Time-Series Forecasting still online?
Free alerts · no account▲ 0Do you run Ephemeris Time-Series Forecasting? Know when it stops answering
For publishers · optionalIts hosted endpoint can be monitored. Monitoring Pro connects every 30 minutes like an AI assistant, emails you within the hour when it stops answering, keeps a 90-day availability history and adds your answer rate to your badge.
Monitoring never changes a score or a rank.
Questions about Ephemeris Time-Series Forecasting
How do I connect Ephemeris Time-Series Forecasting?
Use the hosted endpoint https://ephemeris.cascade.industries/api/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.
Does Ephemeris Time-Series Forecasting need an API key or token?
Yes. The registry entry lists required values: Authorization, EPHEMERIS_API_KEY. Get them from the publisher.
What tools does Ephemeris Time-Series Forecasting offer?
When Electra Index connected on 19 Nov 2026, it listed 7 tools: get_version, describe_forecast, plot_forecast, forecast, list_models, get_balance, get_usage. The full list is in "Live check" above.
Is Ephemeris Time-Series Forecasting online?
Yes. Its hosted endpoint answered an MCP connection from Electra Index 1d ago.
What can I use Ephemeris Time-Series Forecasting for?
Based on its description, it is most relevant to: build financial models, forecast demand, monitor company cash flow, forecast sales pipeline.