# analyze

`station__markov__analyze` · external (needs EXECUTION_BACKEND_URL configured) · domain `markov` · pv-relevance `non-pv`

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

> **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

- `states` *array* (required) — State labels
- `transitions` *array* (required) — Array of {from, to, probability}
- `analysis` *string* (required) — Analysis mode
- `from_state` *integer* — Source state index (for n_step, mfpt)
- `to_state` *integer* — Target state index (for n_step, mfpt)
- `steps` *integer* — 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__markov__analyze",
    "arguments": {
      "states": [],
      "transitions": [],
      "analysis": ""
    }
  }
}
```

## Related

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