io.github.belegante-byte/aetherx-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@io.github.belegante-byte/aetherx-mcp What's the congestion risk at Santos right now?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
aetherx-mcp
MCP server for the Aether-X Port Congestion Oracle — gives any MCP-compatible agent (Claude Desktop, Cursor, VS Code, custom LLM agents) predictive port congestion signals for global trade and quantitative finance.
Install
pip install aetherx-mcp
# or run without installing (recommended for MCP clients):
uvx aetherx-mcpRelated MCP server: Supply Chain Disruption Monitor
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
Tool | Arguments | Returns |
|
| Congestion score, ETA delay, waiting vessels, freight volatility |
|
| Same, for a whole portfolio, fetched in parallel |
| — | The 15 pre-seeded ports (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,
"updated_at": "2026-09-17 15:46:53"
}Configuration
Variable | Default | Description |
| — | When set, requests are routed through the RapidAPI gateway (metered billing) |
|
| RapidAPI host |
|
| Direct API base URL |
Without RAPIDAPI_KEY, the server calls the public production API directly.
Example agent prompts
"What's the congestion risk at Santos right now?"
"Rank these ports by congestion: BRSSZ, CNSHA, NLRTM, USLAX."
"Which of my Asian ports has the highest freight volatility index?"
License
MIT — see LICENSE. The signals are provided "AS IS" and do not constitute investment advice. See the Terms of Service.
Available Tools
3 toolsget_port_riskAInspect
Return the predictive congestion signal for a single port.
Args: port_id: UN/LOCODE of the port, e.g. "BRSSZ" (Santos), "CNSHA" (Shanghai).
Inputs: port_id (required). Returns: object
get_ports_riskAInspect
Return congestion signals for several ports in parallel.
Args: port_ids: list of UN/LOCODEs, e.g. ["BRSSZ", "CNSHA", "NLRTM"].
Inputs: port_ids (required). Returns: result
list_supported_portsAInspect
List the 15 ports pre-seeded in the oracle (id, name, country).
Inputs: no named parameters. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The two risk tools differ only in cardinality (single vs. batch), but the names and descriptions clearly indicate which to use. list_supported_ports is entirely distinct. Minor potential confusion when querying one port, but explicit pluralization disambiguates.
All tools follow a consistent verb_noun snake_case pattern: get_ for queries, list_ for enumeration. Pluralization is used appropriately (port vs. ports), making the naming predictable and readable.
Three tools is minimal but appropriate for a read-only oracle with a fixed dataset. It covers listing, single query, and batch query without unnecessary bloat. Slightly thin, but well-scoped for the domain.
The tool set fully covers the domain: you can discover supported ports via list, query one port, or query many in parallel. There are no obvious dead ends or missing operations for the stated purpose of predictive congestion signals.
Maintenance
Related MCP Connectors
Intelligence subscription protocol for AI agents. Scored, filtered AI intelligence signals via MCP.
Read-only MCP access to DSGHT.ai published foresight and country-grounded claim resolution.
Built-environment forecasts, public benchmarks, and permit or zoning readiness through remote MCP.
Remote MCP endpoint for U.S. home forecasts, public benchmark data, and permit or zoning readiness.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceOcean container shipping intelligence for AI agents — D\&D tariffs, freight rates, vessel schedules, port congestion, inland haulage across 6 major carriers. 24 MCP tools.1MIT
- FlicenseAqualityDmaintenanceMCP server that exposes tools for monitoring supply chain disruptions, including vessel positions, port weather, congestion, and news. Includes an AI agent that synthesizes these sources to assess route risks.5-
- AlicenseNot gradedqualityDmaintenanceProvides real-time, machine-readable ship and port conditions for major US container gateways using AIS data, allowing AI agents to query vessel status, berthing events, and gateway conditions without API keys or signup.1Apache 2.0
- FlicenseNot gradedqualityDmaintenanceProvides container shipping intelligence for AI agents, enabling demurrage & detention calculations, local charges, inland haulage rates, and CFS tariffs across multiple shipping lines, with pay-per-request USDC payments via x402.-