CoinRithm/coinrithm-agent-trading
OfficialRelated Servers
Alternatives to CoinRithm/coinrithm-agent-trading
AlicenseBqualityBmaintenanceAlpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs7212,160 PyPI1,104MIT- AlicenseAqualityDmaintenanceTrade, analyze, and automate Polymarket prediction markets via AI. 34 tools for direct trading, smart money flow, copy trading, backtest, and portfolio management.48115 npm20MIT
Related Servers
- AlicenseBqualityDmaintenanceEnables AI agents to trade crypto with paper money, access market data, view leaderboards, and manage trading bots via an MCP-compatible interface.16MIT
- AlicenseAqualityBmaintenanceEnables AI agents to paper-trade on Polymarket against live order books with realistic fees and fill mechanics, including market search, portfolio tracking, and strategy backtesting.33157 PyPI509MIT
- FlicenseNot gradedqualityDmaintenanceEnables agents to access live crypto market data and execute risk-controlled paper trades through standardized MCP tool calls.-
- AlicenseNot gradedqualityBmaintenanceProvides a safe paper-trading twin of the Binance Agent OS MCP API so agents can be rehearsed, scored, gated for go-live, and shadow-compared against live calls without using real funds.MIT
- FlicenseAqualityCmaintenanceEnables agents to generate alpha signals, retrieve market snapshots, compute portfolio risk, validate and submit paper orders, and trigger a kill switch, all under deterministic pre-trade risk controls and audit logging.5-

bytx-traderofficial
AlicenseNot gradedqualityBmaintenanceEnables AI assistants to scan crypto perpetuals, assess derivatives and entry/exit setups, simulate trades, size positions, run risk checks, and execute paper or demo trades through a gated confirmation workflow.92MIT
TDQS
Scored across 49 tools
Most tools have clearly distinct purposes, and the very detailed descriptions actively cross-reference alternatives (e.g. 'use pm_data_event for full evidence', 'use pm_quote for tradability'). But several near-duplicate names create real misselection risk: pm_data_event vs pm_data_events, pm_data_whales vs pm_data_whale_wallets vs pm_data_whale_wallet, and get_agent_ledger vs export_agent_ledger vs export_run_evidence. The singular/plural event pair and the three-tool whale cluster have boundaries that only careful reading resolves.
There are internally consistent families (pm_data_* research, get_* readers, open_/close_/cancel_/place_ mutators, *_quote), but the overall set mixes conventions: verb-first (get_candles), noun-first with no verb (crypto_price, tradfi_references, instrument_markets), reversed noun_verb (spot_quote, futures_quote), and a bare whoami. It is readable but not predictable as a single scheme.
49 tools is heavy for one server and exceeds the threshold where an agent can hold the surface in context. The domain is genuinely broad (multi-venue PM data, crypto data, spot/futures/PM paper trading, ledger and Arena), but several tools could be consolidated, notably the three whale tools and the multiple ledger/export variants.
Coverage is impressive: discovery, quotes, order placement and cancellation, futures SL/TP, position and balance reads, PnL, equity curve, ledgers, exports and Arena rankings, plus a deep public PM research surface. The main gap is the inability to close a prediction-market position before settlement (open_pm_position exists with no counterpart), and no order-modify operation for spot.