# run-anti-vector-pipeline

`station__microgram__run-anti-vector-pipeline` · external (needs EXECUTION_BACKEND_URL configured) · domain `microgram` · pv-relevance `pv-core`

Signal-to-prescription pipeline: PRR signal detection → anti-vector classification. Takes a PRR value and harm type, returns signal verdict plus the anti-vector strategy (primary class, measures, biases). Completes the sentence from 'there is a signal' to 'here is what to do about it.'

> **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

- `prr` *number* (required) — PRR value for signal detection (threshold: >= 2.0)
- `harm_type` *string* — Harm type: A (Acute), B (Cumulative), C (Off-Target), D (Cascade), E (Idiosyncratic), F (Saturation), G (Interaction), H (Population)
- `signal_magnitude` *number* — Normalized signal magnitude 0.0-1.0 (optional, used for proportionality tier)

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__microgram__run-anti-vector-pipeline",
    "arguments": {
      "prr": 0
    }
  }
}
```

## Related

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