score-geometric
Compute non-compensatory risk score using weighted geometric mean. Default Bayesian-heavy weights [PRR=0.15, ROR=0.15, IC025=0.35, EBGM05=0.35] maximize signal-to-noise discrimination (validated via 40-scenario simulation). A near-zero dimension collapses the composite.
Taxonomy
Linnaean classification joined from the algovigilance taxonomy index via the parent config's rank.
| Rank | Value |
|---|---|
| domain | Substrata |
| kingdom | Constructa |
| phylum | Configa |
| class | station-config |
| order | noncompensatory |
| family | mcp-tool-config |
Characteristics:
- substrate:
config - domain:
pv - lifecycle:
continuous - authority:
read - compounding:
producer - io:
agent-request→tool-response
Input schema
drugstringrequired — Drug nameeventstringrequired — Adverse eventprrnumberrequired — Proportional Reporting Ratioror_lowernumberrequired — ROR lower 95% confidence intervalic025numberrequired — Information Component 2.5th percentileeb05numberrequired — EBGM 5th percentilenintegerrequired — Number of casesweightsstring — Custom weights as comma-separated: PRR,ROR,IC025,EBGM05 (must sum to 1.0). Default: 0.15,0.15,0.35,0.35
Example call
POST /api/mcp
Content-Type: application/json
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "station__noncompensatory__score-geometric",
"arguments": {
"drug": "",
"event": "",
"prr": 0,
"ror_lower": 0,
"ic025": 0,
"eb05": 0,
"n": 0
}
}
}How to invoke from a client
From any MCP-aware client, add https://algovigilance.com/api/mcp as an MCP server, then call this tool by name. From a raw HTTP client, send the JSON-RPC body above to /api/mcp.
Agent-friendly formats
Working inside an AI assistant? Use the Copy for AI button at the top of this page (or view the raw Markdown) to paste a clean, token-budgeted version of this tool's contract into your conversation.
Related
- All tools (3062 live)
- /api/mcp — endpoint
- /AGENTS.md — agent guide
- /tools/noncompensatory__score-geometric/raw.md — this page's Markdown twin