# Microgram: dtree-predict

`station__algovigilance__microgram-dtree-predict` · native (always callable) · domain `algovigilance` · pv-relevance `pv-core`

Run prediction on a fitted decision tree. Pass the tree_json from train and a feature vector. Use when classifying new data points.

## Agent metadata

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

## Input schema

- `tree_json` *string* (required) — Serialized tree from train output
- `features` *object* (required) — Feature values for one sample

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-dtree-predict",
    "arguments": {
      "tree_json": "",
      "features": {}
    }
  }
}
```

## Related

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