Castlebet Aviator

v1.0.0

A powerful MCP server built with NitroStack

Connection Setup

Add via Cursor Settings UI (Settings > Features > MCP > Add New MCP Server): 

{
  "mcpServers": {
    // your other mcp servers
    "castlebet-aviator": {
      "url": "https://play2mcp.zambrite.com/mcp"
    }
  }
}

Connect remote tools directly via Claude's Web UI:

Add custom connector BETA
Connect Claude to your data and tools. Learn more about connectors or get started with pre-built ones.
Advanced settings
Only use connectors from developers you trust. Anthropic does not control which tools developers make available and cannot verify that they will work as intended or that they won't change.
Building an MCP server? Report issues and subscribe to updates here

Configure custom tools directly via ChatGPT's Web UI:

New App
Icon (optional)
PNG only. Best results at 256 x 256 px or larger. Max file size: 10 KB
Name
Description (optional)
Connection
Authentication
Custom MCP servers introduce risk. Learn more
OpenAI hasn't reviewed this MCP server. Attackers may attempt to steal your data or trick the model into taking unintended actions, including destroying data.
Read the guide

Add the following configuration block under mcpServers in your Antigravity configuration file (~/.gemini/config/mcp_config.json): 

{
  "mcpServers": {
    // your other mcp servers
    "castlebet-aviator": {
      "serverUrl": "https://play2mcp.zambrite.com/mcp"
    }
  }
}

Add the following configuration block to your Codex configuration file (~/.codex/config.toml): 

[mcp_servers.castlebet-aviator]
url = "https://play2mcp.zambrite.com/mcp"

Connect directly using the Server-Sent Events endpoint: 

https://play2mcp.zambrite.com/mcp
Available Tools
aviator_get_results

Settled bets from the money ledger, newest first, with a lifetime summary. Each result says whether the bet won, lost, was voided, or never reached the table. The summary always covers full history even when the list is filtered.

aviator_get_performance

Aggregate performance for a profile: bets, wins, losses, turnover, net profit/loss, win rate and ROI, from the money ledger. A negative ROI means the strategy is losing money.

aviator_get_status

Live state of the bot: whether it is running or paused, current balance, session and daily net, round index, loss/win streaks, execution health, and any bet awaiting reconciliation.

aviator_get_stats

Detailed dashboard statistics: totals, streaks, cashout efficiency, plan staleness, and breakdowns by edge tier, target multiplier and hour of day.

aviator_get_pending_reconciliation

The bet blocking the bot, if any, together with every field the system could resolve for it (round number, outcome, settled balance, paid multiplier) and where each value came from. Betting stays stopped until a pending bet is reconciled.

aviator_play

Control the bot. 'start' begins placing REAL MONEY bets under the configured risk limits; 'stop' ends the run; 'pause' and 'resume' hold and release it. Requires a write token. The bot's own safety gates still apply — this cannot force a bet the risk engine refuses.

aviator_place_bet

Run one of the three betting strategies and return what it won or lost. learned — the adaptive engine picks entry, target and confidence itself. `amount` is the TOTAL session allocation, split across `rounds`. bold-once — one bet at a fixed stake and target. Ignores `rounds`. bold-guard — fixed stake at a target or range (e.g. "1.2-1.5"), repeated `rounds` times, stopping if the balance falls below `minBalance`. With mode 'real' this stakes REAL MONEY and requires a write token plus confirm: true. Use mode 'dry' to simulate. If waitSeconds > 0 the call blocks until the run finishes and returns the settled bets; otherwise it returns a jobId to poll with aviator_get_bet_result.

aviator_get_bet_result

Job status plus every bet settled since a run started, with win/loss and net. Pass the jobId and startedAt returned by aviator_place_bet.