@SKalinin909
基本情報
Deterministic crypto futures calculations for AI agents. PnL, liquidation, break-even, position sizing and more via MCP.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"tradingcalc": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://tradingcalc.io/api/mcp"
]
}
}
}Calculate net PnL, ROE, fees and gross profit/loss for a futures trade. Use when user asks "what's my profit/loss on this trade?" Returns: grossPnl, fees, netPnl, netPnlUsdt, roe (%).
Calculate the liquidation price for an isolated-margin futures position. Use when user asks "where will I get liquidated?" or "how close is my liq price?". Returns: liquidationPrice, distancePct (how far from entry).
Calculate the break-even exit price that covers all trading fees. Use when user asks "what price do I need to just break even?" Returns: breakevenPrice, totalFees.
Calculate the correct position size given a maximum risk in USDT and a stop-loss price. Use when user asks "how many coins should I buy?" or "size my position so I risk exactly $X". Returns: positionSize (base), positionUsdt, marginRequired.
Calculate the total funding cost (or income) for holding a perpetual futures position. Use when user asks "how much funding will I pay holding X days?" or "is funding eating my profit?". Returns: totalFundingUsdt (negative = you pay, positive = you receive), perIntervalUsdt.
Calculate the weighted average entry price from multiple buy/sell fills (DCA). Use when user has filled at multiple prices and asks "what's my average entry?" Returns: averagePrice, totalSize, totalCost.
Calculate the exact exit price needed to hit a target PnL or ROE percentage. Use when user asks "at what price do I take profit to make $500?" or "where should I set TP for 20% ROE?". Returns: targetExitPrice.
Run a scenario analysis: compute PnL for multiple price-change percentages at once. Use when user asks "show me my P&L if BTC moves -10%, -5%, +5%, +10%". Returns: array of { deltaPct, exitPrice, netPnl, roe }.
Calculate the maximum safe leverage based on account size, max acceptable drawdown, and asset daily volatility. Use when user asks "what's the max leverage I should use on BTC?" or "how much leverage is safe given 3% daily volatility?". Returns: maxLeverage, marginAtRisk.
Calculate the short perpetual futures position size needed to hedge a spot holding. Use when user asks "how much should I short to hedge my BTC?" or "what margin do I need for a 100% hedge?". Returns: hedgeNotional, requiredMargin, estimatedFundingCost.
Calculate funding rate arbitrage profit: annualized yield, net profit, and breakeven days for a long/short basis trade across two exchanges. Use when user asks "is this funding arb worth it?" or "how many days to break even on transfer fees?". Returns: netProfitUsdt, annualizedYieldPct, breakevenDays.
Project capital growth from reinvesting perpetual futures funding income (compounding carry). Use when user asks "how much will I make compounding 0.01% funding for 90 days?" or "what's my APY on this carry position?". Returns: finalCapital, totalEarned, apy, growthTable.
Full pre-trade decision card: orchestrates position sizing, breakeven, liquidation, and funding cost in one call. Use when user describes a full trade setup and asks "should I take this trade?" or "run the numbers on this setup". Provide exchange+symbol to fetch live funding rate automatically. Returns: positionSize, breakeven, liquidationPrice, fundingCost, overnightBreakevenShift, verdict.
Full risk:reward analysis — the single best tool when user describes a trade with entry, stop, and target. Calculates R:R ratio, position size, liquidation price, breakeven, and P&L at both stop and target. Returns a verdict: strong (3:1+) / good (2:1+) / marginal / poor. Use when user asks "is this trade worth taking?" or "what's my risk reward on this setup?".
DCA entry planner: weighted average entry price, breakeven, and per-level contribution from multiple fill prices and sizes. Use when user bought at several prices and asks "what's my average entry?" or "where is my DCA breakeven?". Returns: averageEntry, breakeven, per-level summary.
Scale-out planner: P&L, ROI, and cumulative P&L for each partial exit level. Use when user wants to take profit at multiple targets — "close 30% at $90k, 30% at $95k, 40% at $100k — what's my total P&L?". Returns: per-level pnl, weightedAvgExitPrice, totalRoi.
Delta-neutral carry trade (funding arbitrage) analysis. Use when user asks "is this carry trade worth it?" — long on exchange A, short on exchange B, collect the funding rate spread. Returns: netYieldPct, grossProfit, netProfit, breakevenDays, verdict (profitable/marginal/loss).
Price move needed to cover funding cost + fees over a holding period. Use when user asks "how much does BTC need to move for me to profit after funding?" or "is funding killing my edge on this trade?". Returns: breakevenWithFunding, breakevenWithoutFunding, requiredMovePct.
Market Profile open analysis — where and how price opened vs the prior session value area. Returns open location, open type (OD/OTD/ORR/OAIR), key levels (VAH/VAL/VPOC/IB), and bullish/bearish/neutral scenario framing. Use for "how did BTC open today?" / "what does the open imply for the session?".
Market Profile day-type classifier — trend / balance / neutral_trend / normal / normal_var, from TPO, initial balance, range extension and value migration. Use for "is this a trend day or a balance day?".
Market Profile value-area migration across sessions — is value migrating up, down, or overlapping (directional conviction vs balance)? Use for "is value moving higher day over day?".
Market Profile breakout acceptance — did price accept (hold) beyond the value area / range, or reject back inside (fakeout)? Optional buy/sell delta. Use for "did the break above VAH get accepted?".
Run the full regression suite — 22 canonical test vectors across all 12 calculators — and return a pass/fail report with counts and timestamp. Call this before using results in production workflows to confirm the computation layer is operating correctly.
Tradingcalc MCP is a deterministic calculation server for futures and crypto trade planning. It provides 19 tools across trade P&L, risk & margin, and funding/carry, returning exact numbers instead of AI guesses. Formulas are verified against 22 canonical test vectors and normalized across 7 exchanges. It is designed for traders, AI agents, and trading bots.
Connect via MCP (Claude Desktop, Cursor, VS Code) or direct HTTP. For Claude Desktop, add a claude_desktop_config.json entry using npx -y mcp-remote https://tradingcalc.io/api/mcp. For Cursor/VS Code, set the url to the same endpoint. Alternatively, send JSON-RPC POST requests to https://tradingcalc.io/api/mcp. An API key is optional for MCP but required for REST endpoints.
system.verify) to confirm correctnessLLMs give plausible but potentially wrong numbers. Tradingcalc MCP returns exact calculations – same inputs always produce the same outputs, eliminating hallucination risk for financial data.
Plans range from Anonymous (20 req/day, free) to Growth (2,000,000 req/day, $599/mo). Credits are consumed per tool: primitives cost 1 credit, standard workflows 5, advanced workflows 8, and the pre-trade check 10 credits.
Email hi@tradingcalc.io to request an API key. Pass it as `Authorization: Bearer <your-api-key>`.
Formulas are normalized for Binance, Bybit, OKX, Hyperliquid, Aster, KuCoin, and MEXC.
It uses Streamable HTTP (MCP specification 2024-11-05).
This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex,
This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent
Multi-Agent AI Orchestration Workshop
Quarkus LangChain4J Workshop that demonstrates both single AI service capabilities and Agentic AI orchestration
コメント