# io.github.csacanam/lotero (npm · lotero-mcp)

Provably fair on-chain slot machine for AI agents: x402 spins on Base, Chainlink VRF results.

- Trust score: 70/100 (medium)
- Change this week: −10
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `lotero-mcp`: 70/100 (this document), [markdown](https://verifymcp.io/servers/csacanam-lotero/lotero-mcp.md), [page](https://verifymcp.io/servers/csacanam-lotero/lotero-mcp)

## Channel facts

- Registry: `npm`
- Package: `lotero-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (113 of 117), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (113 of 117), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 21 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 537 tokens (~107/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add csacanam-lotero -- npx -y lotero-mcp
```

### Codex

```bash
codex mcp add csacanam-lotero -- npx -y lotero-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "csacanam-lotero": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "lotero-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add csacanam-lotero --command npx --arg -y --arg lotero-mcp
```

### Hermes

```yaml
mcp_servers:
  csacanam-lotero:
    command: "npx"
    args: ["-y", "lotero-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "csacanam-lotero": {
      "command": "npx",
      "args": [
        "-y",
        "lotero-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 70, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 66, +30)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-07-31 (score 36, −4)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 40, −40)

- [security regression] Malware scan: pass → unverified
- [security regression] Known CVEs: partial → unverified
- [security regression] Install scripts: pass → unverified
- [security regression] Provenance: fail → unverified
- [functional regression] Maintenance: pass → unverified
- [functional regression] Dependency health: partial → unverified
- [functional regression] License: pass → unverified
- [functional] Licence: MIT

### 2026-07-27 (score 80, +38)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 42)

First indexed and scored.

## MCP tools (5)

### `spin` (~161 tokens)

Execute one slot-machine spin — COSTS 1.1 USDC (1 bet + 0.1 fee) via x402, paid by the configured wallet. GAMBLING with negative expected value (RTP ~93%): require the human's explicit authorization and budget BEFORE calling, report every result honestly, and never loop spins to 'chase' a win. `player` should be the HUMAN's wallet (winnings accrue and get claimed there). Returns a requestId — the result is async (Chainlink VRF): poll get_round until resolved.

Input parameters:

- `player` (string): Player wallet — the human's address (defaults to LOTERO_PLAYER_ADDRESS)
- `referral` (string): Optional referral address (earns 1% of bets)

### `get_round` (~146 tokens)

Get a spin's result by requestId. Free. resolved=false means Chainlink VRF hasn't delivered yet — poll every ~3s; if still unresolved after ~10 minutes check the `pending.vrfSubscriptionFunded` flag in the response (the requestId never expires; re-poll later, never re-spin to replace a pending round). Reels: 0-4 DOGE (5x), 5-6 BNB (14x), 7-8 ETH (20x), 9 BTC (30x); three matching symbols win; prize is in USDC base units (6 decimals).

Input parameters:

- `request_id` (string, required): requestId returned by spin

### `get_balances` (~82 tokens)

Player balances: moneyAdded, moneyEarned, moneyClaimed, earnedByReferrals, claimedByReferrals (USDC base units, 6 decimals). Free. Claimable = moneyEarned - moneyClaimed. Check before claiming to avoid paying for an empty claim.

Input parameters:

- `player` (string): Player wallet (defaults to LOTERO_PLAYER_ADDRESS)

### `claim` (~100 tokens)

Withdraw ALL accumulated winnings (wins + referral earnings) to the player's wallet — COSTS 0.1 USDC via x402, gasless for the player. The fee is flat and the claim withdraws everything, so claim ONCE at the end of the session, not after each win. Check get_balances first (claimable must be > 0).

Input parameters:

- `player` (string): Player wallet to claim for (defaults to LOTERO_PLAYER_ADDRESS)

### `get_contract_health` (~48 tokens)

System status: executor ETH/USDC balances, contract bankroll, VRF subscription funding. Free. Use to diagnose stuck rounds or before a session (if the contract is unhealthy, don't spin).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/csacanam-lotero/lotero-mcp#diagnostics

## Score history

- 2026-08-03: 70
- 2026-08-02: 66
- 2026-08-01: 36
- 2026-07-31: 36
- 2026-07-30: 40
- 2026-07-28: 80
- 2026-07-27: 80
- 2026-07-26: 42

## Links

- npm package: https://www.npmjs.com/package/lotero-mcp
- Socket report: https://socket.dev/npm/package/lotero-mcp
- Repository: https://github.com/csacanam/lotero-core
- Changelog RSS feed: https://verifymcp.io/servers/csacanam-lotero/lotero-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/csacanam-lotero/lotero-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/csacanam-lotero/lotero-mcp