mcpField
A
Aether-X Port Delay Intelligence

Aether-X Port Delay Intelligence

Remote
aetherx.aether-grid.ioMaps & Travel0Updated 3w ago

About Aether-X Port Delay Intelligence

Aether-X Port Delay Intelligence is an MCP server for port congestion and maritime delay data, aimed at logistics and supply-chain decisions. It combines port status and risk signals with per-result source and timestamp information.

Key features

  1. 01Port status and delay queries
  2. 02Congestion and demurrage risk metrics
  3. 03Portfolio risk checks across ports
  4. 0424/48/72-hour congestion projections
  5. 05Supported ports and chokepoint listing

Use cases

  1. 01Check whether a port is delayed
  2. 02Compare congestion risk across a port portfolio
  3. 03Review vessel queues and daily demurrage estimates
  4. 04Inspect projected congestion trends

MCP support

It exposes port operations, risk, trend, and supported-port tools to MCP clients. Results include data-source provenance and an as-of timestamp.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://aetherx.aether-grid.io/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
pypiaetherx-mcp0.2.5

Tools

26
ParameterTypeRequiredDescription
port_idstringYes

Details

From the project README

aetherx-mcp — Port Congestion, Maritime Logistics & Supply Chain MCP Server

Aether-X is an MCP server for the Aether-X Port Congestion Oracle that gives any MCP-compatible agent (Claude Desktop, Cursor, VS Code, custom LLM agents) port congestion, maritime delay, vessel queue and supply-chain risk signals for global trade — answered in plain language for simple queries ("is Rotterdam delayed?") and in USD exposure for decision-grade workflows (demurrage, charter risk, fiscal arbitrage across routes).

Keywords: maritime, shipping, vessels, ports, port congestion, demurrage, freight, logistics, supply chain, ETA delay, vessel queue, chokepoints, Suez, Panama, trade lanes, cargo, quantitative finance.

DATA INTEGRITY NOTICE: Brazilian ports (BRSSZ Santos, BRPNG Paranaguá, BRRIO Rio de Janeiro) feed live operational line-ups (data_source="live:appa+santos+lachmann"); Niterói (BRNIT) and Itaguaí (BRITG) together with Rio de Janeiro feed live line-up from SILOG PortosRio (data_source="live:portosrio_silog"). The remaining ports serve a static reference seed (data_source="static_reference_seed"). Every tool result includes data_source and as_of. The 24/48/72h trend is a synthetic projection, not a live forecast. Seed values are NOT real-time field data.

Install

pip install aetherx-mcp
# or run without installing (recommended for MCP clients):
uvx aetherx-mcp

Configure your MCP client

Claude Desktop (claude_desktop_config.json)
{
  "mcpServers": {
    "aetherx-oracle": {
      "command": "uvx",
      "args": ["aetherx-mcp"],
      "env": { "RAPIDAPI_KEY": "SUA_RAPIDAPI_KEY" }
    }
  }
}
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "aetherx-oracle": {
      "command": "uvx",
      "args": ["aetherx-mcp"],
      "env": { "RAPIDAPI_KEY": "SUA_RAPIDAPI_KEY" }
    }
  }
}

Tools

ToolArgumentsReturns
get_port_operations_statusport_id (UN/LOCODE)Plain-language status (NORMAL / CONGESTED), delay, waiting vessels, source provenance + optional decision-layer upsell — free observation
get_port_riskport_id (UN/LOCODE)Congestion score, ETA delay, waiting vessels, freight volatility, daily demurrage estimate
get_ports_riskport_ids (list)Same, for a whole portfolio, fetched in parallel
get_port_trendport_id (UN/LOCODE)24h / 48h / 72h congestion projection + trend label (acelerando / estável / descongestionando)
list_supported_ports—The 35 ports & chokepoints (id, name, country)

Every response is a typed payload:

{
  "port_id": "BRSSZ",
  "port_name": "Santos",
  "country": "Brasil",
  "congestion_score": 0.78,
  "eta_delay_days": 1.6,
  "waiting_vessels": 12,
  "freight_volatility_index": 0.42,
  "estimated_daily_demurrage_usd": 63200,
  "updated_at": "2026-09-17 15:46:53"
}

Configuration

VariableDefaultDescription
RAPIDAPI_KEY—When set, requests are routed through the RapidAPI gateway (metered billing)
RAPIDAPI_HOSTaether-x-port-congestion-oracle.p.rapidapi.comRapidAPI host
AETHERX_BASE_URLhttps://aetherx.aether-grid.ioDirect API base URL

Without RAPIDAPI_KEY, the server calls the public production API directly.

Example agent prompts

  • "Is the port of Santos delayed right now?" (→ get_port_operations_status)
  • "Where is my cargo stuck? What's the waiting time at Paranaguá?" (→ get_port_operations_status)
  • "What's the congestion risk at Rotterdam over the next 3 days?" (→ get_port_trend, forecast_vessel_queue_delays)
  • "Rank these ports by congestion: BRSSZ, CNSHA, NLRTM, USLAX." (→ get_ports_risk)
  • "How many ships are waiting at Shanghai?" (→ get_port_state, get_port_operations_status)
  • "Which route minimizes demurrage + fiscal cost for my fertilizer cargo to MT?" (→ evaluate_fiscal_routing, requires M2M key)

License

MIT — see LICENSE. The signals are provided "AS IS" and do not constitute investment advice. See the Terms of Service.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.