# risk-score

`station__vigilance__risk-score` · external (needs EXECUTION_BACKEND_URL configured) · domain `vigilance` · pv-relevance `pv-core`

Compute Guardian-AV risk score (0-10) for a drug-event pair from four disproportionality metrics and case count. Levels: minimal (<2), low (2-4), moderate (4-6), high (6-8), critical (>=8). Combines signal magnitude, CI confidence, Bayesian evidence, information content, and reporting volume.

> **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

- `drug` *string* (required) — Drug name or identifier
- `event` *string* (required) — Adverse event term (MedDRA preferred term recommended)
- `prr` *number* (required) — Proportional Reporting Ratio value
- `ror_lower` *number* (required) — ROR lower 95% confidence interval
- `ic025` *number* (required) — IC lower credibility interval (IC025)
- `eb05` *number* (required) — EBGM 5th percentile (EB05)
- `n` *integer* (required) — Number of case reports for this drug-event pair

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__vigilance__risk-score",
    "arguments": {
      "drug": "",
      "event": "",
      "prr": 0,
      "ror_lower": 0,
      "ic025": 0,
      "eb05": 0,
      "n": 0
    }
  }
}
```

## Related

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