# compute-qbri

`station__benefit-risk__compute-qbri` · external (needs EXECUTION_BACKEND_URL configured) · domain `benefit-risk` · pv-relevance `pv-core`

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.

> **Note:** This tool routes through an external execution backend. If `EXECUTION_BACKEND_URL` is unset on the server, calls return JSON-RPC error `-32603 "Tool execution backend not configured"`. Tools with `backend: native` execute in-process and are always callable.

## Agent metadata

- `idempotent`: unknown
- `read_only`: unknown
- `expected_latency_ms`: unknown (not yet contract-tested)
- `cost_tokens_estimate`: unknown

## Input schema

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

## Example call

```json
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
    }
  }
}
```

## Related

- [/tools](/tools) — all 3062 tools
- [/tools/benefit-risk__compute-qbri](/tools/benefit-risk__compute-qbri) — HTML page
- [/tools/benefit-risk__compute-qbri/json](/tools/benefit-risk__compute-qbri/json) — JSON form (agent-friendly)
- [/api/mcp](/api/mcp) — endpoint
- [/AGENTS.md](/AGENTS.md) — agent guide