# Microgram: antivector-antivector-compute

`station__algovigilance__microgram-antivector-antivector-compute` · native (always callable) · domain `algovigilance` · pv-relevance `pv-core`

Compute a complete anti-vector for a drug-event harm vector. Returns mechanistic, epistemic, and architectural components with annihilation result (residual harm / annihilated / surplus protection).

## Agent metadata

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

## Input schema

- `bias_magnitude` *number* — Bias magnitude (0.0 to 1.0, required if bias_type provided).
- `bias_type` *string* — Bias type to assess (optional): indication, notoriety, weber, channeling, protopathic, depletion, stimulated, duplicate.
- `confidence` *number* (required) — Input parameter confidence.
- `drug` *string* (required) — Drug or intervention name.
- `event` *string* (required) — Adverse event or harm outcome.
- `harm_type` *string* (required) — Harm type letter: A-I.
- `magnitude` *number* (required) — Signal magnitude (0.0 to 1.0).
- `pathway` *string* — Optional causal pathway description.

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-antivector-antivector-compute",
    "arguments": {
      "confidence": 0,
      "drug": "",
      "event": "",
      "harm_type": "",
      "magnitude": 0
    }
  }
}
```

## Related

- [/tools](/tools) — all 7718 tools
- [/tools/algovigilance__microgram-antivector-antivector-compute](/tools/algovigilance__microgram-antivector-antivector-compute) — HTML page
- [/tools/algovigilance__microgram-antivector-antivector-compute/json](/tools/algovigilance__microgram-antivector-antivector-compute/json) — JSON form (agent-friendly)
- [/api/mcp](/api/mcp) — endpoint
- [/AGENTS.md](/AGENTS.md) — agent guide