# Microgram: markov-analyze

`station__algovigilance__microgram-markov-analyze` · native (always callable) · domain `algovigilance` · pv-relevance `pv-core`

Analyze a Markov chain. Modes: summary, stationary, n_step, classify, classes, ergodicity, entropy, mfpt.

## Agent metadata

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

## Input schema

- `states` *object* (required) — State labels
- `transitions` *object* (required) — Array of {from, to, probability}
- `analysis` *string* (required) — Analysis mode
- `from_state` *number* — Source state index (for n_step, mfpt)
- `to_state` *number* — Target state index (for n_step, mfpt)
- `steps` *number* — Number of steps (for n_step, default 1)

## Example call

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

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__algovigilance__microgram-markov-analyze",
    "arguments": {
      "states": {},
      "transitions": {},
      "analysis": ""
    }
  }
}
```

## Related

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