{
  "schema_version": "0.1",
  "name": "AI Fin Hub Tools",
  "description": "33 client-side AI-in-markets tools — calculators, comparators, playgrounds, generators, directories. All run in-browser; no server-side API. BYO API key where LLM calls are involved.",
  "tools": [
    {
      "name": "kelly_sizer",
      "description": "Map conviction tiers to fractional Kelly bet sizes with a drawdown Monte Carlo simulator. Client-side. Private by default.",
      "url": "https://aifinhub.io/kelly-sizer/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "win_probability": {
            "type": "number"
          },
          "win_loss_ratio": {
            "type": "number"
          },
          "kelly_fraction": {
            "type": "number"
          },
          "bankroll": {
            "type": "number"
          },
          "per_trade_cap_percent": {
            "type": "number"
          },
          "monte_carlo_trials": {
            "type": "integer"
          },
          "trades_per_path": {
            "type": "integer"
          }
        },
        "required": [
          "tool",
          "win_probability",
          "win_loss_ratio",
          "kelly_fraction",
          "bankroll",
          "per_trade_cap_percent",
          "monte_carlo_trials",
          "trades_per_path"
        ]
      }
    },
    {
      "name": "backtest_overfitting_score",
      "description": "Upload a backtest trade log and compute Probability of Backtest Overfitting (PBO), Deflated Sharpe Ratio, and the odds your edge survives live trading.",
      "url": "https://aifinhub.io/backtest-overfitting-score/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "returns_csv_header": {
            "type": "string"
          },
          "variants_count": {
            "type": "integer"
          },
          "trading_days": {
            "type": "integer"
          },
          "best_variant_sharpe": {
            "type": "number"
          },
          "cscv_splits": {
            "type": "integer"
          }
        },
        "required": [
          "tool",
          "returns_csv_header",
          "variants_count",
          "trading_days",
          "best_variant_sharpe",
          "cscv_splits"
        ]
      }
    },
    {
      "name": "data_vendor_tco",
      "description": "Compute annual cost of market data across Databento, Polygon, Alpaca, Tiingo, FMP, and Alpha Vantage for your exact universe, bar resolution, history depth, and API call volume.",
      "url": "https://aifinhub.io/data-vendor-tco/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "symbol_count": {
            "type": "integer"
          },
          "bar_resolution": {
            "type": "string",
            "enum": [
              "tick",
              "1s",
              "1m",
              "5m",
              "1h",
              "1d"
            ]
          },
          "years_history": {
            "type": "number"
          },
          "include_l2_book": {
            "type": "boolean"
          },
          "api_calls_per_day": {
            "type": "integer"
          },
          "vendors": {
            "type": "array",
            "items": {
              "type": "string"
            }
          }
        },
        "required": [
          "tool",
          "symbol_count",
          "bar_resolution",
          "years_history",
          "include_l2_book",
          "api_calls_per_day",
          "vendors"
        ]
      }
    },
    {
      "name": "finance_mcp_directory",
      "description": "Security-graded catalog of finance MCP servers — Alpaca, Polygon, Databento, IBKR, Tradier, Tiingo, NautilusTrader. Scope, auth, idempotency, transport, schema quality, all in one place.",
      "url": "https://aifinhub.io/finance-mcp-directory/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "filter_by_venue": {
            "type": "string"
          },
          "filter_by_scope": {
            "type": "string"
          },
          "min_security_grade": {
            "type": "string",
            "enum": [
              "A",
              "B",
              "C",
              "D",
              "F"
            ]
          }
        },
        "required": [
          "tool"
        ]
      }
    },
    {
      "name": "token_cost_optimizer",
      "description": "Compute the dollar cost of a trading research loop across Claude, GPT, and Gemini. Prompt length × model × retry × call volume → cost per idea and per validated trade.",
      "url": "https://aifinhub.io/token-cost-optimizer/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "prompt_input_tokens": {
            "type": "integer"
          },
          "prompt_output_tokens": {
            "type": "integer"
          },
          "model": {
            "type": "string"
          },
          "calls_per_idea": {
            "type": "integer"
          },
          "retry_rate": {
            "type": "number"
          },
          "ideas_per_day": {
            "type": "integer"
          },
          "days_per_month": {
            "type": "integer"
          }
        },
        "required": [
          "tool",
          "prompt_input_tokens",
          "prompt_output_tokens",
          "model",
          "calls_per_idea",
          "retry_rate",
          "ideas_per_day",
          "days_per_month"
        ]
      }
    },
    {
      "name": "agent_skill_tester",
      "description": "Paste a SKILL.md definition + sample input + your Anthropic API key. See structured extraction, token cost, and latency — all in your browser. No signup, key never leaves the page.",
      "url": "https://aifinhub.io/agent-skill-tester/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "skill_md": {
            "type": "string"
          },
          "sample_input_text": {
            "type": "string"
          },
          "model": {
            "type": "string"
          },
          "max_output_tokens": {
            "type": "integer"
          },
          "anthropic_api_key": {
            "type": "string"
          }
        },
        "required": [
          "tool",
          "skill_md",
          "sample_input_text",
          "model",
          "max_output_tokens",
          "anthropic_api_key"
        ]
      }
    },
    {
      "name": "prompt_regression_tester",
      "description": "Run the same prompt against multiple models (Claude 4.5/4.6/4.7, GPT-5, Gemini 2.5) with your own keys. Diff outputs, score drift, catch regressions before they hit your production agent.",
      "url": "https://aifinhub.io/prompt-regression-tester/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "prompt": {
            "type": "string"
          },
          "models": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "anthropic_api_key": {
            "type": "string"
          },
          "openai_api_key": {
            "type": "string"
          },
          "google_api_key": {
            "type": "string"
          },
          "runs_per_model": {
            "type": "integer"
          }
        },
        "required": [
          "tool",
          "prompt",
          "models",
          "runs_per_model"
        ]
      }
    },
    {
      "name": "hallucination_detector",
      "description": "Paste a source document + an LLM's extraction. Every numeric claim in the output is checked against the source. Client-side. Catches silent fabrication before it ends up in your pipeline.",
      "url": "https://aifinhub.io/hallucination-detector/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "source_document": {
            "type": "string"
          },
          "llm_output": {
            "type": "string"
          },
          "strict_mode": {
            "type": "boolean"
          }
        },
        "required": [
          "tool",
          "source_document",
          "llm_output",
          "strict_mode"
        ]
      }
    },
    {
      "name": "kalshi_poly_arb",
      "description": "Daily-refreshed scan of arbitrage candidates across Kalshi and Polymarket. Paired contract matching, tax + resolution-risk overlay, no signup. Edge data rendered client-side from static JSON.",
      "url": "https://aifinhub.io/kalshi-poly-arb/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "min_edge_bps": {
            "type": "number"
          },
          "max_tax_haircut_percent": {
            "type": "number"
          },
          "include_resolution_risk_flags": {
            "type": "boolean"
          },
          "venues": {
            "type": "array",
            "items": {
              "type": "string"
            }
          }
        },
        "required": [
          "tool",
          "min_edge_bps",
          "max_tax_haircut_percent",
          "include_resolution_risk_flags",
          "venues"
        ]
      }
    },
    {
      "name": "order_book_replay",
      "description": "Drop a Level-2 CSV and watch the book reconstruct tick by tick. Animated depth bars, best bid/ask, spread over time. Understand microstructure before you design your strategy.",
      "url": "https://aifinhub.io/order-book-replay/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "csv_header": {
            "type": "string"
          },
          "playback_speed_multiplier": {
            "type": "number"
          },
          "max_levels_rendered": {
            "type": "integer"
          },
          "focus_symbol": {
            "type": "string"
          }
        },
        "required": [
          "tool",
          "csv_header",
          "playback_speed_multiplier",
          "max_levels_rendered",
          "focus_symbol"
        ]
      }
    },
    {
      "name": "calibration_dojo",
      "description": "Train your probabilistic intuition. Answer binary forecasting questions at any confidence level; track Brier score and reliability curve over time. All state stored locally.",
      "url": "https://aifinhub.io/calibration-dojo/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "session_length_questions": {
            "type": "integer"
          },
          "difficulty": {
            "type": "string",
            "enum": [
              "easy",
              "medium",
              "hard"
            ]
          },
          "domain_filter": {
            "type": "string"
          }
        },
        "required": [
          "tool",
          "session_length_questions",
          "difficulty",
          "domain_filter"
        ]
      }
    },
    {
      "name": "trading_system_blueprinter",
      "description": "Pick your data source, LLM, broker, storage, risk engine, and logger. Get a Mermaid architecture diagram, a starter repo scaffold (ZIP), and a list of open-source integrations that actually compose.",
      "url": "https://aifinhub.io/trading-system-blueprinter/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "data_source": {
            "type": "string"
          },
          "llm_provider": {
            "type": "string"
          },
          "broker": {
            "type": "string"
          },
          "storage": {
            "type": "string"
          },
          "risk_engine": {
            "type": "string"
          },
          "logger": {
            "type": "string"
          }
        },
        "required": [
          "tool",
          "data_source",
          "llm_provider",
          "broker",
          "storage",
          "risk_engine",
          "logger"
        ]
      }
    },
    {
      "name": "risk_adjusted_returns",
      "description": "Paste a returns CSV. Sharpe, Sortino, Calmar, Omega, alpha, beta, tracking error, information ratio, max drawdown, and tail moments — plus a benchmark-relative block when you include one.",
      "url": "https://aifinhub.io/risk-adjusted-returns/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "returns_csv_header": {
            "type": "string"
          },
          "periods_per_year": {
            "type": "integer"
          },
          "risk_free_rate_annual": {
            "type": "number"
          },
          "mar_annual": {
            "type": "number"
          }
        },
        "required": [
          "tool",
          "returns_csv_header",
          "periods_per_year",
          "risk_free_rate_annual",
          "mar_annual"
        ]
      }
    },
    {
      "name": "walk_forward_validator",
      "description": "Upload a returns CSV. Rolling or expanding IS/OOS windows, per-window Sharpe, walk-forward efficiency, and a concatenated OOS equity curve. Catches regime decay that PBO alone misses.",
      "url": "https://aifinhub.io/walk-forward-validator/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "returns_csv_header": {
            "type": "string"
          },
          "window_mode": {
            "type": "string",
            "enum": [
              "rolling",
              "expanding"
            ]
          },
          "is_window_days": {
            "type": "integer"
          },
          "oos_window_days": {
            "type": "integer"
          },
          "step_days": {
            "type": "integer"
          },
          "periods_per_year": {
            "type": "integer"
          }
        },
        "required": [
          "tool",
          "returns_csv_header",
          "window_mode",
          "is_window_days",
          "oos_window_days",
          "step_days",
          "periods_per_year"
        ]
      }
    },
    {
      "name": "options_greeks_explorer",
      "description": "Black-Scholes pricer + live Greeks visualizer. Drag spot, strike, vol, DTE, rate, dividend yield — see delta, gamma, theta, vega, rho update with the payoff curve. Call + put.",
      "url": "https://aifinhub.io/options-greeks-explorer/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "option_type": {
            "type": "string",
            "enum": [
              "call",
              "put"
            ]
          },
          "spot": {
            "type": "number"
          },
          "strike": {
            "type": "number"
          },
          "annual_vol": {
            "type": "number"
          },
          "days_to_expiry": {
            "type": "integer"
          },
          "risk_free_rate": {
            "type": "number"
          },
          "dividend_yield": {
            "type": "number"
          }
        },
        "required": [
          "tool",
          "option_type",
          "spot",
          "strike",
          "annual_vol",
          "days_to_expiry",
          "risk_free_rate",
          "dividend_yield"
        ]
      }
    },
    {
      "name": "correlation_matrix_visualizer",
      "description": "Paste a multi-asset returns CSV. See the Pearson correlation heatmap, condition number, average absolute correlation, and eigenvalue concentration — the diagnostics for detecting redundant strategies before you allocate capital.",
      "url": "https://aifinhub.io/correlation-matrix-visualizer/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "returns_csv_header": {
            "type": "string"
          },
          "min_observations": {
            "type": "integer"
          },
          "max_columns_rendered": {
            "type": "integer"
          }
        },
        "required": [
          "tool",
          "returns_csv_header",
          "min_observations",
          "max_columns_rendered"
        ]
      }
    },
    {
      "name": "returns_distribution_analyzer",
      "description": "Paste a returns CSV. Histogram, normal-overlay, QQ plot, skewness, excess kurtosis, Jarque-Bera test, tail-weight index. See why Sharpe alone misleads when your distribution has fat tails.",
      "url": "https://aifinhub.io/returns-distribution-analyzer/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "returns_csv_header": {
            "type": "string"
          },
          "histogram_bins": {
            "type": "integer"
          },
          "tail_sigma_threshold": {
            "type": "number"
          }
        },
        "required": [
          "tool",
          "returns_csv_header",
          "histogram_bins",
          "tail_sigma_threshold"
        ]
      }
    },
    {
      "name": "price_blind_auditor",
      "description": "Paste a research prompt or agent context bundle. The auditor flags price numbers, directional words, and outcome-leaking phrases that cause LLMs to retroactively rationalize positions. Builds a price-blind research boundary.",
      "url": "https://aifinhub.io/price-blind-auditor/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "prompt_text": {
            "type": "string"
          },
          "include_low_severity": {
            "type": "boolean"
          }
        },
        "required": [
          "tool",
          "prompt_text",
          "include_low_severity"
        ]
      }
    },
    {
      "name": "prompt_injection_tester",
      "description": "Red-team a finance agent against 24 documented prompt-injection attacks — direct override, role confusion, indirect injection via retrieved content, jailbreak patterns, tool-call hijack. BYO key; runs client-side against your live model.",
      "url": "https://aifinhub.io/prompt-injection-tester/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "provider": {
            "type": "string",
            "enum": [
              "anthropic",
              "openai",
              "google"
            ]
          },
          "model": {
            "type": "string"
          },
          "api_key": {
            "type": "string"
          },
          "target_system_prompt": {
            "type": "string"
          },
          "include_categories": {
            "type": "array",
            "items": {
              "type": "string"
            }
          }
        },
        "required": [
          "tool",
          "provider",
          "model",
          "api_key",
          "target_system_prompt",
          "include_categories"
        ]
      }
    },
    {
      "name": "efficient_frontier_builder",
      "description": "Paste a multi-asset returns CSV. See the Markowitz mean-variance frontier, the minimum-variance portfolio, the max-Sharpe (tangency) portfolio, and the per-asset weights for each highlighted point. Closed-form solution, client-side.",
      "url": "https://aifinhub.io/efficient-frontier-builder/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "returns_csv_header": {
            "type": "string"
          },
          "risk_free_rate_annual": {
            "type": "number"
          },
          "periods_per_year": {
            "type": "integer"
          },
          "frontier_steps": {
            "type": "integer"
          },
          "short_selling_allowed": {
            "type": "boolean"
          }
        },
        "required": [
          "tool",
          "returns_csv_header",
          "risk_free_rate_annual",
          "periods_per_year",
          "frontier_steps",
          "short_selling_allowed"
        ]
      }
    },
    {
      "name": "options_payoff_builder",
      "description": "Build 1–4 leg option strategies. Pick call/put, long/short, strike, and contracts. See the at-expiry payoff diagram, break-even points, maximum profit and loss, and the aggregated Greeks at current spot. Presets for straddle, strangle, iron condor, spreads, butterfly.",
      "url": "https://aifinhub.io/options-payoff-builder/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "spot": {
            "type": "number"
          },
          "annual_vol": {
            "type": "number"
          },
          "days_to_expiry": {
            "type": "integer"
          },
          "risk_free_rate": {
            "type": "number"
          },
          "dividend_yield": {
            "type": "number"
          },
          "legs": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "side": {
                  "type": "string",
                  "enum": [
                    "long",
                    "short"
                  ]
                },
                "option_type": {
                  "type": "string",
                  "enum": [
                    "call",
                    "put"
                  ]
                },
                "strike": {
                  "type": "number"
                },
                "contracts": {
                  "type": "integer"
                }
              }
            }
          }
        },
        "required": [
          "tool",
          "spot",
          "annual_vol",
          "days_to_expiry",
          "risk_free_rate",
          "dividend_yield",
          "legs"
        ]
      }
    },
    {
      "name": "pair_trading_tester",
      "description": "Paste two price series. Engle-Granger cointegration test: OLS hedge ratio, Augmented Dickey-Fuller on residuals, Ornstein-Uhlenbeck half-life, z-score time series with configurable entry/exit bands. Everything client-side.",
      "url": "https://aifinhub.io/pair-trading-tester/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "prices_csv_header": {
            "type": "string"
          },
          "adf_lags": {
            "type": "integer"
          },
          "z_window": {
            "type": "integer"
          },
          "entry_z": {
            "type": "number"
          },
          "exit_z": {
            "type": "number"
          }
        },
        "required": [
          "tool",
          "prices_csv_header",
          "adf_lags",
          "z_window",
          "entry_z",
          "exit_z"
        ]
      }
    },
    {
      "name": "execution_simulator",
      "description": "Square-root impact + linear temporary impact + latency jitter. See the real slippage of any trade size before you route it.",
      "url": "https://aifinhub.io/execution-simulator/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "side": {
            "type": "string",
            "enum": [
              "buy",
              "sell"
            ]
          },
          "order_size_shares": {
            "type": "number"
          },
          "adv_shares": {
            "type": "number"
          },
          "spread_bps": {
            "type": "number"
          },
          "daily_vol_pct": {
            "type": "number"
          },
          "participation_pct": {
            "type": "number"
          },
          "latency_ms": {
            "type": "number"
          },
          "latency_jitter_ms": {
            "type": "number"
          },
          "reference_price_usd": {
            "type": "number"
          }
        },
        "required": [
          "tool",
          "side",
          "order_size_shares",
          "adv_shares",
          "spread_bps",
          "daily_vol_pct",
          "participation_pct"
        ]
      }
    },
    {
      "name": "broker_api_comparator",
      "description": "Compare Alpaca, IBKR, Tradier, Schwab, Robinhood on authentication, rate limits, order types, market data, MCP availability, and fees.",
      "url": "https://aifinhub.io/broker-api-comparator/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "must_support": {
            "type": "array",
            "items": {
              "type": "string",
              "enum": [
                "stocks",
                "options",
                "futures",
                "crypto",
                "forex",
                "bonds"
              ]
            }
          },
          "mcp_required": {
            "type": "boolean"
          },
          "free_tier_required": {
            "type": "boolean"
          },
          "max_auth_complexity": {
            "type": "integer",
            "minimum": 1,
            "maximum": 5
          }
        },
        "required": [
          "tool"
        ]
      }
    },
    {
      "name": "synthetic_market_data_generator",
      "description": "Generate synthetic price series — geometric Brownian motion, GARCH(1,1) with volatility clustering, regime-switching bull/bear, or copula-linked pairs. Download CSV/JSON for backtest scaffolding.",
      "url": "https://aifinhub.io/synthetic-market-data-generator/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          },
          "model": {
            "type": "string",
            "enum": [
              "gbm",
              "garch",
              "regime",
              "pair"
            ]
          },
          "seed": {
            "type": "integer"
          },
          "starting_price_usd": {
            "type": "number"
          },
          "annualized_drift_pct": {
            "type": "number"
          },
          "annualized_vol_pct": {
            "type": "number"
          },
          "days": {
            "type": "integer"
          },
          "trading_days_per_year": {
            "type": "integer"
          },
          "garch_omega": {
            "type": "number"
          },
          "garch_alpha": {
            "type": "number"
          },
          "garch_beta": {
            "type": "number"
          },
          "bull_drift_pct": {
            "type": "number"
          },
          "bear_drift_pct": {
            "type": "number"
          },
          "p_bull_to_bear": {
            "type": "number"
          },
          "p_bear_to_bull": {
            "type": "number"
          },
          "rho": {
            "type": "number",
            "minimum": -1,
            "maximum": 1
          }
        },
        "required": [
          "tool",
          "model",
          "days"
        ]
      }
    },
    {
      "name": "financial_document_token_estimator",
      "description": "Paste a 10-K, 10-Q, 8-K or earnings transcript and see token count + one-pass extraction cost across eight frontier LLMs, with cache-hit toggle and context-window fit check.",
      "url": "https://aifinhub.io/financial-document-token-estimator/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          }
        },
        "required": [
          "tool"
        ]
      }
    },
    {
      "name": "sec_filing_chunk_optimizer",
      "description": "Pick a filing archetype, tune chunk size and overlap, and see chunk count, embedding cost, and structural-boundary warnings across three chunking strategies.",
      "url": "https://aifinhub.io/sec-filing-chunk-optimizer/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          }
        },
        "required": [
          "tool"
        ]
      }
    },
    {
      "name": "structured_schema_validator_finance",
      "description": "Paste LLM JSON output and validate against four pre-built finance schemas — research output, trade decision, risk snapshot, peer comparison — with sanity checks on unit and GAAP basis.",
      "url": "https://aifinhub.io/structured-schema-validator-finance/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          }
        },
        "required": [
          "tool"
        ]
      }
    },
    {
      "name": "agent_cost_envelope_calculator",
      "description": "Model an LLM research loop end-to-end — steps, tool calls, convergence checks, markets per day — and see per-loop, daily, and monthly cost with cost-cap recommendations.",
      "url": "https://aifinhub.io/agent-cost-envelope-calculator/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          }
        },
        "required": [
          "tool"
        ]
      }
    },
    {
      "name": "fallback_chain_simulator",
      "description": "Define a provider fallback chain, simulate rate-limit and latency failures, and see p50/p95/p99 latency, success rate, total cost, and degradation-event distribution.",
      "url": "https://aifinhub.io/fallback-chain-simulator/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          }
        },
        "required": [
          "tool"
        ]
      }
    },
    {
      "name": "model_selector_finance",
      "description": "Input task, latency budget, cost budget, context size, and quality sensitivity; get ranked model recommendations with rationale — grounded in published pricing and vendor capabilities, not benchmark scores.",
      "url": "https://aifinhub.io/model-selector-finance/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          }
        },
        "required": [
          "tool"
        ]
      }
    },
    {
      "name": "batch_vs_realtime_cost_calculator",
      "description": "Jobs per day, tokens per job, model, deadline — get real-time vs batch cost side-by-side with savings estimate and batch-eligibility flag. Based on vendor-published batch pricing.",
      "url": "https://aifinhub.io/batch-vs-realtime-cost-calculator/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          }
        },
        "required": [
          "tool"
        ]
      }
    },
    {
      "name": "forecast_scoring_sandbox",
      "description": "Paste a forecast stream (probability + outcome) and see Brier score with full decomposition, log loss, reliability diagram, and bootstrap confidence intervals. Works on any prob + binary outcome CSV.",
      "url": "https://aifinhub.io/forecast-scoring-sandbox/",
      "inputSchema": {
        "type": "object",
        "properties": {
          "tool": {
            "type": "string"
          }
        },
        "required": [
          "tool"
        ]
      }
    }
  ],
  "disclaimer": "Planning estimates only — not financial, tax, or investment advice.",
  "creator": {
    "@type": "Organization",
    "name": "Orbyd",
    "url": "https://orbyd.app"
  }
}