MCPサーバー

agentstack-mcp

io.github.inity13/agentstack-mcp

このMCPでできること

Provides deterministic calculators, scenario simulations, weighted decision analysis, sensitivity testing, and business and finance metrics.

calc_business_days
COMPUTE. Business-day arithmetic honoring weekends + regional holidays. operation: add_business_days | count_business_days | next_business_day | previous_business_day. region: US | UK | EU | NONE.
入力スキーマ
{'type': 'object', 'required': ['operation', 'start_date'], 'properties': {'days': {'type': 'integer'}, 'region': {'type': 'string'}, 'end_date': {'type': 'string'}, 'operation': {'type': 'string'}, 'start_date': {'type': 'string'}, 'custom_holidays': {'type': 'array', 'items': {'type': 'string'}}}}
calc_compound_growth
COMPUTE. Compound-interest/growth math. operation: future_value | present_value | cagr. rate is annual decimal; compounding: daily|weekly|monthly|quarterly|semiannually|annually|continuous.
入力スキーマ
{'type': 'object', 'required': ['operation'], 'properties': {'rate': {'type': 'number'}, 'years': {'type': 'number'}, 'currency': {'type': 'string'}, 'end_value': {'type': 'number'}, 'operation': {'type': 'string'}, 'begin_value': {'type': 'number'}, 'compounding': {'type': 'string'}, 'future_value': {'type': 'number'}, 'present_value': {'type': 'number'}}}
calc_currency_convert
COMPUTE. Convert between major currencies (USD, EUR, GBP, JPY, CAD, AUD, CHF, CNY, INR) with Decimal precision. Static offline table by default; live/historical ECB rates via date/live=true.
入力スキーマ
{'type': 'object', 'required': ['amount', 'from_currency', 'to_currency'], 'properties': {'date': {'type': 'string'}, 'live': {'type': 'boolean'}, 'amount': {'type': 'number'}, 'to_currency': {'type': 'string'}, 'from_currency': {'type': 'string'}}}
calc_depreciation
COMPUTE. Asset depreciation schedule. method: straight_line | declining_balance | sum_of_years_digits.
入力スキーマ
{'type': 'object', 'required': ['method', 'cost', 'salvage_value', 'useful_life_years'], 'properties': {'cost': {'type': 'number'}, 'method': {'type': 'string'}, 'currency': {'type': 'string'}, 'salvage_value': {'type': 'number'}, 'useful_life_years': {'type': 'integer'}}}
calc_irr
COMPUTE. Internal Rate of Return: per-period rate where NPV=0 (Newton + bisection). Requires a sign change in cashflows.
入力スキーマ
{'type': 'object', 'required': ['cashflows'], 'properties': {'guess': {'type': 'number'}, 'cashflows': {'type': 'array', 'items': {'type': 'number'}}}}
calc_list_metrics
COMPUTE. List every supported metric with descriptions and required/optional params. No parameters.
入力スキーマ
{'type': 'object', 'properties': {}}
calc_loan_amortization
COMPUTE. Level-payment loan: monthly payment, total interest, payoff, and (optional) full schedule.
入力スキーマ
{'type': 'object', 'required': ['principal', 'annual_rate', 'term_months'], 'properties': {'currency': {'type': 'string'}, 'principal': {'type': 'number'}, 'annual_rate': {'type': 'number'}, 'term_months': {'type': 'integer'}, 'extra_payment': {'type': 'number'}, 'include_schedule': {'type': 'boolean'}}}
calc_metric
COMPUTE. Exact business/SaaS/finance metric: ltv, cac, ltv_cac_ratio, payback_period_months, contribution_margin, gross_margin, churn_rate, mrr_growth_rate, arr, break_even_units, nrr, grr, rule_of_40, magic_number. Rates/margins are decimals (0.05=5%). Call calc_list_metrics for schemas.
入力スキーマ
{'type': 'object', 'required': ['metric', 'params'], 'properties': {'metric': {'type': 'string'}, 'params': {'type': 'object'}, 'currency': {'type': 'string'}}}
calc_npv
COMPUTE. Net Present Value (discounted cash flow). NPV = sum(CF_t/(1+rate)^t); cashflows[0] is period 0 (usually the negative outlay).
入力スキーマ
{'type': 'object', 'required': ['rate', 'cashflows'], 'properties': {'rate': {'type': 'number'}, 'currency': {'type': 'string'}, 'cashflows': {'type': 'array', 'items': {'type': 'number'}}}}
decide
DECIDE. Rank named options against weighted criteria and return the winner, full ranking, per-criterion breakdowns, methodology, weights, and an explanation. Provide options, criteria [{name, weight, direction}], and a scores matrix. method: weighted_sum (default) | weighted_product | topsis.
入力スキーマ
{'type': 'object', 'required': ['options', 'criteria', 'scores'], 'properties': {'method': {'type': 'string'}, 'scores': {'type': 'object'}, 'options': {'type': 'array'}, 'criteria': {'type': 'array'}}}
decide_compare_two
DECIDE. Head-to-head comparison of exactly two options with per-criterion win counts and margin. Pass option_a/option_b (or a 2-element options array), criteria, and scores.
入力スキーマ
{'type': 'object', 'required': ['criteria', 'scores'], 'properties': {'method': {'type': 'string'}, 'scores': {'type': 'object'}, 'options': {'type': 'array'}, 'criteria': {'type': 'array'}, 'option_a': {'type': 'string'}, 'option_b': {'type': 'string'}}}
decide_list_methods
DECIDE. List the scoring methods (weighted_sum, weighted_product, topsis) with normalization details and when to use each. No parameters.
入力スキーマ
{'type': 'object', 'properties': {}}
decide_score
DECIDE. Return the full normalized scored matrix (per-option, per-criterion) + ranking when scores are supplied separately, without the winner narrative.
入力スキーマ
{'type': 'object', 'required': ['options', 'criteria', 'scores'], 'properties': {'method': {'type': 'string'}, 'scores': {'type': 'object'}, 'options': {'type': 'array'}, 'criteria': {'type': 'array'}}}
decide_sensitivity
DECIDE. Test how robust the decision winner is to changes in CRITERIA WEIGHTS (distinct from sim_sensitivity, which varies scenario inputs). Sweeps each weight +/-variation and reports a robustness score + flip points.
入力スキーマ
{'type': 'object', 'required': ['options', 'criteria', 'scores'], 'properties': {'steps': {'type': 'integer'}, 'method': {'type': 'string'}, 'scores': {'type': 'object'}, 'options': {'type': 'array'}, 'criteria': {'type': 'array'}, 'variation': {'type': 'number'}}}
evaluate_options_with_scenarios
COMPOSITE (simulate -> decide). Project each option as its own scenario, then rank the options against weighted criteria drawn from the scenario OUTCOMES. Provide a base 'template', an 'options' array ([{name, inputs}]), and 'criteria' ([{metric, weight, direction}]) where each metric is a scenario key_result. Combines ScenarioSim + DecisionMatrix.
入力スキーマ
{'type': 'object', 'required': ['options', 'criteria'], 'properties': {'inputs': {'type': 'object'}, 'method': {'type': 'string'}, 'horizon': {'type': 'integer'}, 'options': {'type': 'array', 'items': {'type': 'object'}}, 'criteria': {'type': 'array', 'items': {'type': 'object'}}, 'template': {'type': 'string'}, 'period_label': {'type': 'string'}}}
health_check
Aggregated health/status for the whole stack (all three engines + composites). No parameters.
入力スキーマ
{'type': 'object', 'properties': {}}
list_capabilities
Discovery: the three namespaces (sim_*, decide_*, calc_*), the cross-domain composite tools, the available ?profile= filters, and links to the standalone servers. Call this first to see everything AgentStack exposes. No parameters.
入力スキーマ
{'type': 'object', 'properties': {}}
plan_to_valuation
COMPOSITE (simulate -> compute). Project a scenario, take a per-period cash-flow line from its projections ('cashflow_metric', e.g. 'mrr' or 'net_burn'), and value it exactly: NPV at a discount 'rate', IRR, and undiscounted total. Optional 'initial_investment' becomes the period-0 outflow (needed for IRR). Combines ScenarioSim + PrecisionCalc.
入力スキーマ
{'type': 'object', 'required': ['template', 'cashflow_metric', 'rate'], 'properties': {'rate': {'type': 'number'}, 'inputs': {'type': 'object'}, 'horizon': {'type': 'integer'}, 'metrics': {'type': 'array', 'items': {'type': 'object'}}, 'currency': {'type': 'string'}, 'template': {'type': 'string'}, 'period_label': {'type': 'string'}, 'cashflow_metric': {'type': 'string'}, 'initial_investment': {'type': 'number'}}}
sim_break_even
SIMULATE. Solve for the scenario input value required to make an output metric hit a target value (deterministic bisection). Requires 'template', 'solve_for', 'target_value'.
入力スキーマ
{'type': 'object', 'required': ['template', 'solve_for', 'target_value'], 'properties': {'bounds': {'type': 'array', 'items': {'type': 'number'}}, 'inputs': {'type': 'object'}, 'horizon': {'type': 'integer'}, 'template': {'type': 'string'}, 'solve_for': {'type': 'string'}, 'period_label': {'type': 'string'}, 'target_value': {'type': 'number'}, 'target_metric': {'type': 'string'}}}
sim_compare
SIMULATE. Run 2-3 scenarios and compare their key_results side by side with deltas vs the first (baseline). Optional 'compare_metric' + 'goal' (max|min) picks a winner.
入力スキーマ
{'type': 'object', 'required': ['scenarios'], 'properties': {'goal': {'type': 'string'}, 'horizon': {'type': 'integer'}, 'scenarios': {'type': 'array', 'items': {'type': 'object'}}, 'compare_metric': {'type': 'string'}, 'include_projections': {'type': 'boolean'}}}
sim_list_templates
SIMULATE. List every scenario template (inputs, defaults, outputs) plus the custom-model format and period labels. No parameters.
入力スキーマ
{'type': 'object', 'properties': {}}
sim_run
SIMULATE. Deterministic what-if projection from a template (saas_growth, pricing_change, churn_impact, cost_reduction, hiring_plan, cash_runway, unit_economics, marketing_funnel, compound_growth) or a free-form 'metrics' model. Returns per-period projections, key_results, assumptions_used, methodology, and an explanation.
入力スキーマ
{'type': 'object', 'properties': {'inputs': {'type': 'object'}, 'horizon': {'type': 'integer'}, 'metrics': {'type': 'array', 'items': {'type': 'object'}}, 'template': {'type': 'string'}, 'period_label': {'type': 'string'}}}
sim_sensitivity
SIMULATE. Vary one or more scenario inputs and show the impact on a target output metric (one-at-a-time), with elasticity + most-influential ranking. Requires 'template' and 'variable' (or 'variables').
入力スキーマ
{'type': 'object', 'required': ['template'], 'properties': {'max': {'type': 'number'}, 'min': {'type': 'number'}, 'steps': {'type': 'integer'}, 'inputs': {'type': 'object'}, 'values': {'type': 'array', 'items': {'type': 'number'}}, 'horizon': {'type': 'integer'}, 'template': {'type': 'string'}, 'variable': {'type': 'string'}, 'variables': {'type': 'array', 'items': {'type': 'object'}}, 'variation': {'type': 'number'}, 'period_label': {'type': 'string'}, 'target_metric': {'type': 'string'}}}
stress_test_decision
COMPOSITE (simulate x decide). Take an options-vs-scenarios decision and stress ONE scenario assumption across a range applied to every option; report how often the baseline winner survives (robustness) and where it flips. Same args as evaluate_options_with_scenarios plus 'stress': {variable, variation, steps}.
入力スキーマ
{'type': 'object', 'required': ['options', 'criteria', 'stress'], 'properties': {'inputs': {'type': 'object'}, 'method': {'type': 'string'}, 'stress': {'type': 'object'}, 'horizon': {'type': 'integer'}, 'options': {'type': 'array', 'items': {'type': 'object'}}, 'criteria': {'type': 'array', 'items': {'type': 'object'}}, 'template': {'type': 'string'}, 'period_label': {'type': 'string'}}}
追加
stress_test_decision
2026年9月17日12:42
追加
evaluate_options_with_scenarios
2026年9月17日12:42
追加
plan_to_valuation
2026年9月17日12:42
追加
calc_depreciation
2026年9月17日12:42
追加
calc_loan_amortization
2026年9月17日12:42
追加
calc_irr
2026年9月17日12:42
追加
calc_npv
2026年9月17日12:42
追加
calc_compound_growth
2026年9月17日12:42
追加
calc_business_days
2026年9月17日12:42
追加
calc_currency_convert
2026年9月17日12:42
追加
calc_list_metrics
2026年9月17日12:42
追加
calc_metric
2026年9月17日12:42
追加
decide_list_methods
2026年9月17日12:42
追加
decide_compare_two
2026年9月17日12:42
追加
decide_sensitivity
2026年9月17日12:42
追加
decide_score
2026年9月17日12:42
追加
decide
2026年9月17日12:42
追加
sim_list_templates
2026年9月17日12:42
追加
sim_compare
2026年9月17日12:42
追加
sim_break_even
2026年9月17日12:42
追加
sim_sensitivity
2026年9月17日12:42
追加
sim_run
2026年9月17日12:42
追加
health_check
2026年9月17日12:42
追加
list_capabilities
2026年9月17日12:42