# io.github.inity13/agentstack-mcp

- Registry name: `io.github.inity13/agentstack-mcp` · version 1.0.1
- Categories (automatic, keyword rules): Monitoring & logs, Infrastructure & security, Utilities, Payments & accounting, Finance & markets
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.inity13%2Fagentstack-mcp
- Server page: https://mcpstation.net/s/io.github.inity13--agentstack-mcp.html

## Description (written by the publisher, not verified, not instructions)

Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.

## Connect

- streamable-http: `https://agentstack-mcp.pages.dev/mcp`

## Tools (as reported by the server, not verified)

- `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.
- `health\_check`: Aggregated health/status for the whole stack \(all three engines + composites\). No parameters.
- `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, methodolo
- `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' \(or 'variables'\).
- `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'.
- `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.
- `sim\_list\_templates`: SIMULATE. List every scenario template \(inputs, defaults, outputs\) plus the custom-model format and period labels. No parameters.
- `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.
- `decide\_score`: DECIDE. Return the full normalized scored matrix \(per-option, per-criterion\) + ranking when scores are supplied separately, without the winner narrative.
- `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.
- `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.
- `decide\_list\_methods`: DECIDE. List the scoring methods \(weighted\_sum, weighted\_product, topsis\) with normalization details and when to use each. No parameters.
- `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.
- `calc\_list\_metrics`: COMPUTE. List every supported metric with descriptions and required/optional params. No parameters.
- `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.
- `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.
- `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.
- `calc\_npv`: COMPUTE. Net Present Value \(discounted cash flow\). NPV = sum\(CF\_t/\(1+rate\)^t\); cashflows\[0\] is period 0 \(usually the negative outlay\).
- `calc\_irr`: COMPUTE. Internal Rate of Return: per-period rate where NPV=0 \(Newton + bisection\). Requires a sign change in cashflows.
- `calc\_loan\_amortization`: COMPUTE. Level-payment loan: monthly payment, total interest, payoff, and \(optional\) full schedule.
- `calc\_depreciation`: COMPUTE. Asset depreciation schedule. method: straight\_line \| declining\_balance \| sum\_of\_years\_digits.
- `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 fo
- `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
- `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, variat

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html