← home · ← tools · View as Markdown (.md) · JSON

compute-qbri

station__benefit-risk__compute-qbri external (needs EXECUTION_BACKEND_URL) benefit-risk pv-core Constructa Configa

Compute the Quantitative Benefit-Risk Index (QBRI) from benefit and risk parameters. QBRI = (B × Pb × Ub) / (R × Pr × Sr × Tr). Returns index value, decision (Approve/Monitor/More Data/Reject), and confidence. Use after gathering trial efficacy data and post-market safety signals.

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	`benefit`
family	`mcp-tool-config`

Characteristics:

substrate: config
domain: pv
lifecycle: continuous
authority: read
compounding: producer
io: agent-request → tool-response

Input schema

benefit_effect numberrequired — Benefit effect size (e.g., hazard ratio, odds ratio from clinical trial)
benefit_pvalue numberrequired — P-value from clinical trial efficacy endpoint (0-1)
unmet_need numberrequired — Unmet medical need score (1-10, where 10 = no existing treatment)
risk_signal numberrequired — Risk signal strength (e.g., PRR or ROR value from FAERS)
risk_probability numberrequired — Causal probability (0-1, from Naranjo or WHO-UMC assessment)
risk_severity integerrequired — Severity on Hartwig-Siegel scale (1=mild to 7=fatal)
reversible boolean — Whether the adverse event is reversible (default: true)

Example call

POST /api/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__benefit-risk__compute-qbri",
    "arguments": {
      "benefit_effect": 0,
      "benefit_pvalue": 0,
      "unmet_need": 0,
      "risk_signal": 0,
      "risk_probability": 0,
      "risk_severity": 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.

All tools (3062 live)
/api/mcp — endpoint
/AGENTS.md — agent guide
/tools/benefit-risk__compute-qbri/raw.md — this page's Markdown twin