The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Aether X Port Congestion Oracle listing page.
Port congestion signals for developers, AI agents, logistics systems and quantitative workflows.
DATA INTEGRITY NOTICE: Brazilian ports (Santos BRSSZ, Paranaguá BRPNG, Rio BRRIO, Niterói BRNIT, Itaguaí BRITG) serve live line-ups from official port authorities and operations panels (
data_source="live:appa+santos+lachmann"/live:portosrio_silog), refreshed continuously. 12 mapped global ports upgrade tolive:shipinfo_aiswhenever the AIS sensor delivers data. Every remaining port serves a calibrated/static reference seed (calibrated_reference_seed/static_reference_seed) — a modeled baseline, never disguised as live telemetry. Every API/MCP response includesdata_source,decision_gradeandas_ofso you know exactly which is which.
Aether-X is physical-world port intelligence — port congestion signal, vessel queue intelligence, port delay risk / ETA delay, and demurrage exposure — covering 35 ports & global chokepoints (5 Brazilian ports LIVE from official-authority line-ups; 12 global ports live whenever the AIS sensor delivers; the rest calibrated/static reference seed). Delivered through a REST API, a typed Python SDK and a remote MCP server for AI agents.
When to call Aether-X: when a decision depends on current port conditions — choosing between ports, routing cargo, vessel scheduling, ETA risk, demurrage exposure, or supply-chain disruption — not static port information. Every response includes a machine-readable signal block (level, live_observation, queue_vessels, decision_implication, as_of).
Free tier available. No credit card required.
Get a free API key on the RapidAPI listing.
Ask your agent directly:
"What's the congestion risk at Santos?"
"Compare Santos, Shanghai and Rotterdam."
"Which of these ports has the highest modeled demurrage exposure?"
"Show me the 72-hour congestion trend for Santos."
Available tools: get_port_risk · get_ports_risk · get_port_trend
Add to your MCP client config:
Published in the Official MCP Registry as io.github.belegante-byte/aetherx-mcp, available on PyPI, Glama and Smithery.
Base URL: https://aetherx.aether-grid.io
| Method | Path | Description |
|---|---|---|
GET | /v1/port-risk?port_id=BRSSZ | Congestion score, ETA delay, waiting vessels, freight volatility and daily demurrage for one port |
GET | /v1/ports-risk?port_ids=... | Same signal for up to 20 ports in a single call |
GET | /v1/port-trend?port_id=BRSSZ | 24h / 48h / 72h congestion projection with trend label |
GET | /mcp | Remote MCP endpoint (Streamable HTTP) |
Example response (/v1/port-risk?port_id=BRSSZ):
Interactive docs: Swagger UI · OpenAPI
BRSSZ BRRIO CNSHA CNNGB CNTAO SGSIN NLRTM USLAX USNYC DEHAM MPTNG AEDXB KRPUS GBLGP ZACPT MXZLO
Unknown ports fall back to a global statistical estimate (country="Global").
Free Developer Tier — $0.00 for development, prototyping, CI and evaluation. No credit card required.
| Plan | Price | Best for |
|---|---|---|
| Free Developer Tier | $0.00 | Evaluation, prototypes, CI — up to the plan's monthly request limit |
| Pay-as-you-go | $0.02 / query | Production traffic beyond the free tier |
Grab a key on the RapidAPI listing.
io.github.belegante-byte/aetherx-mcpDeploys to Railway via railway.json; the DuckDB oracle is seeded idempotently at boot.
Signals are provided "AS IS", without warranty, and do not constitute investment advice. See Terms of Service.
The Python SDK is MIT licensed. The API, reference engine and data pipeline are proprietary — hosted usage is governed by the Terms.