io.github.inity13/agentstack-mcp

Official24 toolsLive

by inity13 · JavaScript

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

AgentStack MCP (Model Context Protocol Server)

AgentStack MCP exposes a Model Context Protocol endpoint that provides a deterministic reasoning stack for AI agents. It simulates, decides, and computes via tools (ScenarioSim, DecisionMatrix, PrecisionCalc), and also offers cross-domain composite tools that chain these steps, using one API key.

🛠️ Key Features

Single MCP endpoint using model-context-protocol
Deterministic simulate → decide → compute workflow
Stateless operation (no database, no sessions)
40-digit precision with decimal.js (never floats)
24 tools total

🚀 Use Cases

Scenario simulation and decision analysis
Financial modeling with deterministic outputs
Valuation-style calculations using concepts like npv and irr

⚡ Developer Benefits

Identical inputs produce byte-identical output
Decimal-based computations for precision-sensitive agent tools
Streamable HTTP support (topic: streamable-http)

⚠️ Limitations

Stateless design implies no stored state between calls

Topics

agent-toolsai-agentscloudflare-workersdecision-analysisdeterministicfinancial-modelingirrllmmcpmcp-servermodel-context-protocolnpvscenario-simulationstreamable-http

Captured live from the server via tools/list.

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.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

health_check

Aggregated health/status for the whole stack (all three engines + composites). No parameters.

Parameters

No parameters.

Raw schema

{
  "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.

Parameters5

template	string	optional
inputs	object	optional
metrics	array	optional
horizon	integer	optional
period_label	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "template": {
      "type": "string"
    },
    "inputs": {
      "type": "object"
    },
    "metrics": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "horizon": {
      "type": "integer"
    },
    "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').

Parameters12

template	string	required
inputs	object	optional
target_metric	string	optional
variable	string	optional
variables	array	optional
variation	number	optional
steps	integer	optional
values	array	optional
min	number	optional
max	number	optional
horizon	integer	optional
period_label	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "template": {
      "type": "string"
    },
    "inputs": {
      "type": "object"
    },
    "target_metric": {
      "type": "string"
    },
    "variable": {
      "type": "string"
    },
    "variables": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "variation": {
      "type": "number"
    },
    "steps": {
      "type": "integer"
    },
    "values": {
      "type": "array",
      "items": {
        "type": "number"
      }
    },
    "min": {
      "type": "number"
    },
    "max": {
      "type": "number"
    },
    "horizon": {
      "type": "integer"
    },
    "period_label": {
      "type": "string"
    }
  },
  "required": [
    "template"
  ]
}

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'.

Parameters8

template	string	required
inputs	object	optional
solve_for	string	required
target_metric	string	optional
target_value	number	required
bounds	array	optional
horizon	integer	optional
period_label	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "template": {
      "type": "string"
    },
    "inputs": {
      "type": "object"
    },
    "solve_for": {
      "type": "string"
    },
    "target_metric": {
      "type": "string"
    },
    "target_value": {
      "type": "number"
    },
    "bounds": {
      "type": "array",
      "items": {
        "type": "number"
      }
    },
    "horizon": {
      "type": "integer"
    },
    "period_label": {
      "type": "string"
    }
  },
  "required": [
    "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.

Parameters5

scenarios	array	required
compare_metric	string	optional
goal	string	optional
horizon	integer	optional
include_projections	boolean	optional

Raw schema

{
  "type": "object",
  "properties": {
    "scenarios": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "compare_metric": {
      "type": "string"
    },
    "goal": {
      "type": "string"
    },
    "horizon": {
      "type": "integer"
    },
    "include_projections": {
      "type": "boolean"
    }
  },
  "required": [
    "scenarios"
  ]
}

sim_list_templates

SIMULATE. List every scenario template (inputs, defaults, outputs) plus the custom-model format and period labels. No parameters.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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.

Parameters4

options	array	required
criteria	array	required
scores	object	required
method	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "options": {
      "type": "array"
    },
    "criteria": {
      "type": "array"
    },
    "scores": {
      "type": "object"
    },
    "method": {
      "type": "string"
    }
  },
  "required": [
    "options",
    "criteria",
    "scores"
  ]
}

decide_score

DECIDE. Return the full normalized scored matrix (per-option, per-criterion) + ranking when scores are supplied separately, without the winner narrative.

Parameters4

options	array	required
criteria	array	required
scores	object	required
method	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "options": {
      "type": "array"
    },
    "criteria": {
      "type": "array"
    },
    "scores": {
      "type": "object"
    },
    "method": {
      "type": "string"
    }
  },
  "required": [
    "options",
    "criteria",
    "scores"
  ]
}

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.

Parameters6

options	array	required
criteria	array	required
scores	object	required
method	string	optional
variation	number	optional
steps	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "options": {
      "type": "array"
    },
    "criteria": {
      "type": "array"
    },
    "scores": {
      "type": "object"
    },
    "method": {
      "type": "string"
    },
    "variation": {
      "type": "number"
    },
    "steps": {
      "type": "integer"
    }
  },
  "required": [
    "options",
    "criteria",
    "scores"
  ]
}

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.

Parameters6

option_a	string	optional
option_b	string	optional
options	array	optional
criteria	array	required
scores	object	required
method	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "option_a": {
      "type": "string"
    },
    "option_b": {
      "type": "string"
    },
    "options": {
      "type": "array"
    },
    "criteria": {
      "type": "array"
    },
    "scores": {
      "type": "object"
    },
    "method": {
      "type": "string"
    }
  },
  "required": [
    "criteria",
    "scores"
  ]
}

decide_list_methods

DECIDE. List the scoring methods (weighted_sum, weighted_product, topsis) with normalization details and when to use each. No parameters.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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.

Parameters3

metric	string	required
params	object	required
currency	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "metric": {
      "type": "string"
    },
    "params": {
      "type": "object"
    },
    "currency": {
      "type": "string"
    }
  },
  "required": [
    "metric",
    "params"
  ]
}

calc_list_metrics

COMPUTE. List every supported metric with descriptions and required/optional params. No parameters.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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.

Parameters5

amount	number	required
from_currency	string	required
to_currency	string	required
date	string	optional
live	boolean	optional

Raw schema

{
  "type": "object",
  "properties": {
    "amount": {
      "type": "number"
    },
    "from_currency": {
      "type": "string"
    },
    "to_currency": {
      "type": "string"
    },
    "date": {
      "type": "string"
    },
    "live": {
      "type": "boolean"
    }
  },
  "required": [
    "amount",
    "from_currency",
    "to_currency"
  ]
}

calc_business_days

Parameters6

operation	string	required
start_date	string	required
days	integer	optional
end_date	string	optional
region	string	optional
custom_holidays	array	optional

Raw schema

{
  "type": "object",
  "properties": {
    "operation": {
      "type": "string"
    },
    "start_date": {
      "type": "string"
    },
    "days": {
      "type": "integer"
    },
    "end_date": {
      "type": "string"
    },
    "region": {
      "type": "string"
    },
    "custom_holidays": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "operation",
    "start_date"
  ]
}

calc_compound_growth

Parameters9

operation	string	required
rate	number	optional
years	number	optional
present_value	number	optional
future_value	number	optional
begin_value	number	optional
end_value	number	optional
compounding	string	optional
currency	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "operation": {
      "type": "string"
    },
    "rate": {
      "type": "number"
    },
    "years": {
      "type": "number"
    },
    "present_value": {
      "type": "number"
    },
    "future_value": {
      "type": "number"
    },
    "begin_value": {
      "type": "number"
    },
    "end_value": {
      "type": "number"
    },
    "compounding": {
      "type": "string"
    },
    "currency": {
      "type": "string"
    }
  },
  "required": [
    "operation"
  ]
}

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).

Parameters3

rate	number	required
cashflows	array	required
currency	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "rate": {
      "type": "number"
    },
    "cashflows": {
      "type": "array",
      "items": {
        "type": "number"
      }
    },
    "currency": {
      "type": "string"
    }
  },
  "required": [
    "rate",
    "cashflows"
  ]
}

calc_irr

COMPUTE. Internal Rate of Return: per-period rate where NPV=0 (Newton + bisection). Requires a sign change in cashflows.

Parameters2

cashflows	array	required
guess	number	optional

Raw schema

{
  "type": "object",
  "properties": {
    "cashflows": {
      "type": "array",
      "items": {
        "type": "number"
      }
    },
    "guess": {
      "type": "number"
    }
  },
  "required": [
    "cashflows"
  ]
}

calc_loan_amortization

COMPUTE. Level-payment loan: monthly payment, total interest, payoff, and (optional) full schedule.

Parameters6

principal	number	required
annual_rate	number	required
term_months	integer	required
extra_payment	number	optional
currency	string	optional
include_schedule	boolean	optional

Raw schema

{
  "type": "object",
  "properties": {
    "principal": {
      "type": "number"
    },
    "annual_rate": {
      "type": "number"
    },
    "term_months": {
      "type": "integer"
    },
    "extra_payment": {
      "type": "number"
    },
    "currency": {
      "type": "string"
    },
    "include_schedule": {
      "type": "boolean"
    }
  },
  "required": [
    "principal",
    "annual_rate",
    "term_months"
  ]
}

calc_depreciation

COMPUTE. Asset depreciation schedule. method: straight_line | declining_balance | sum_of_years_digits.

Parameters5

method	string	required
cost	number	required
salvage_value	number	required
useful_life_years	integer	required
currency	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "method": {
      "type": "string"
    },
    "cost": {
      "type": "number"
    },
    "salvage_value": {
      "type": "number"
    },
    "useful_life_years": {
      "type": "integer"
    },
    "currency": {
      "type": "string"
    }
  },
  "required": [
    "method",
    "cost",
    "salvage_value",
    "useful_life_years"
  ]
}

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.

Parameters9

template	string	required
inputs	object	optional
metrics	array	optional
horizon	integer	optional
period_label	string	optional
cashflow_metric	string	required
rate	number	required
initial_investment	number	optional
currency	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "template": {
      "type": "string"
    },
    "inputs": {
      "type": "object"
    },
    "metrics": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "horizon": {
      "type": "integer"
    },
    "period_label": {
      "type": "string"
    },
    "cashflow_metric": {
      "type": "string"
    },
    "rate": {
      "type": "number"
    },
    "initial_investment": {
      "type": "number"
    },
    "currency": {
      "type": "string"
    }
  },
  "required": [
    "template",
    "cashflow_metric",
    "rate"
  ]
}

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.

Parameters7

template	string	optional
inputs	object	optional
horizon	integer	optional
period_label	string	optional
method	string	optional
options	array	required
criteria	array	required

Raw schema

{
  "type": "object",
  "properties": {
    "template": {
      "type": "string"
    },
    "inputs": {
      "type": "object"
    },
    "horizon": {
      "type": "integer"
    },
    "period_label": {
      "type": "string"
    },
    "method": {
      "type": "string"
    },
    "options": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "criteria": {
      "type": "array",
      "items": {
        "type": "object"
      }
    }
  },
  "required": [
    "options",
    "criteria"
  ]
}

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}.

Parameters8

template	string	optional
inputs	object	optional
horizon	integer	optional
period_label	string	optional
method	string	optional
options	array	required
criteria	array	required
stress	object	required

Raw schema

{
  "type": "object",
  "properties": {
    "template": {
      "type": "string"
    },
    "inputs": {
      "type": "object"
    },
    "horizon": {
      "type": "integer"
    },
    "period_label": {
      "type": "string"
    },
    "method": {
      "type": "string"
    },
    "options": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "criteria": {
      "type": "array",
      "items": {
        "type": "object"
      }
    },
    "stress": {
      "type": "object"
    }
  },
  "required": [
    "options",
    "criteria",
    "stress"
  ]
}

README.md10 KBView on GitHub

AgentStack MCP

One deterministic reasoning stack for AI agents — behind a single Model Context Protocol (MCP) endpoint and one API key:

simulate (ScenarioSim) → decide (DecisionMatrix) → compute (PrecisionCalc)

plus cross-domain composite tools that chain the three. Every number runs through decimal.js at 40-digit precision (never floats), so identical inputs always produce byte-identical output. The server is stateless — no database, no sessions.

AgentStack bundles three standalone MCP servers so an agent installs one server, uses one key, and can run reasoning that spans all three domains. It imports the same engines directly (no HTTP proxying) — zero added latency, no cascading failure.

🌐 Live hosted server (free, no install)

code

https://agentstack-mcp.pages.dev/mcp

json

{ "mcpServers": { "agentstack": {
    "type": "http", "url": "https://agentstack-mcp.pages.dev/mcp" } } }

Free tier: no key, 20 calls/day per IP. Paid plans (Starter $19/mo · 8,000/day, Pro $59/mo · 80,000/day) return an API key sent as X-API-Key. One key covers all three products and the composites — about half the cost of subscribing to them separately. Landing page: https://agentstack-mcp.pages.dev.

The three namespaces (24 tools)

namespace	engine	tools
`sim_*`	ScenarioSim — what-if / scenario simulation	`sim_run`, `sim_sensitivity`, `sim_break_even`, `sim_compare`, `sim_list_templates`
`decide_*`	DecisionMatrix — multi-criteria decision analysis	`decide`, `decide_score`, `decide_sensitivity`, `decide_compare_two`, `decide_list_methods`
`calc_*`	PrecisionCalc — exact finance/business math	`calc_metric`, `calc_list_metrics`, `calc_currency_convert`, `calc_business_days`, `calc_compound_growth`, `calc_npv`, `calc_irr`, `calc_loan_amortization`, `calc_depreciation`
meta	—	`list_capabilities`, `health_check`

Note on two deliberately-namespaced collisions: sim_sensitivity varies scenario inputs; decide_sensitivity varies criteria weights. They are different operations — the prefix disambiguates them for the agent.

Composite tools — the reason to use the stack

Deterministic end-to-end; each chains engines that no single server bundles:

Tool	Pipeline	What it does
`plan_to_valuation`	simulate → compute	Project a scenario, take a per-period cash-flow line (`cashflow_metric`), and value it: NPV at a discount `rate`, IRR, undiscounted total. `initial_investment` becomes the period-0 outflow (needed for IRR).
`evaluate_options_with_scenarios`	simulate → decide	Project each option as its own scenario, then rank the options against weighted criteria drawn from the scenario outcomes (`key_results`).
`stress_test_decision`	simulate × decide	Stress one scenario assumption across every option and report how often the baseline winner survives (robustness) and where it flips.

Composite responses report the pipeline they ran and carry each stage's structured output, so an agent can drill into any step.

Profiles — fight tool-selection noise

Append ?profile= to the endpoint to load only a subset:

profile	tools
`all` (default)	every tool (24)
`finance`	`calc_*` + `plan_to_valuation` + meta
`decision`	`decide_*` + `evaluate_options_with_scenarios` + `stress_test_decision` + meta
`simulation`	`sim_*` + all composites + meta

json

{ "mcpServers": { "agentstack": {
    "url": "https://agentstack-mcp.pages.dev/mcp?profile=finance" } } }

Response envelope

Namespaced tools return the exact envelope of their underlying product. Composite tools add composite, pipeline, per-stage blocks, methodology, notes, and a plain-language explanation. Errors are always structured data:

json

{ "status": "error", "error": { "type": "unknown_metric", "message": "...", "hint": "..." } }

Example — plan_to_valuation (trimmed):

json

{
  "status": "success",
  "composite": "plan_to_valuation",
  "pipeline": ["scenariosim.run_scenario", "precisioncalc.net_present_value", "precisioncalc.internal_rate_of_return"],
  "scenario": { "template": "saas_growth", "horizon": 12, "key_results": { "ending_mrr": 26982.1 } },
  "cashflow_metric": "mrr",
  "cashflows": [-150000, 14040, 15600, "..."],
  "valuation": { "discount_rate": 0.01, "npv": 11157.386023, "irr": 0.02504, "value_creating": true },
  "explanation": "Projecting 'saas_growth' over 12 month(s) and valuing the 'mrr' stream at 1%/period gives an NPV of ..."
}

Project structure

code

agentstack-mcp/
├── worker-src/
│   ├── index.mjs           # Cloudflare Pages Function: MCP transport, namespacing, profiles, billing
│   ├── composites.mjs      # the 3 cross-domain tools (simulate -> decide -> compute)
│   ├── billing.mjs         # Stripe + KV: one key / one quota for the whole stack
│   └── engines/            # vendored, unmodified product engines (100% deterministic)
│       ├── scenariosim.mjs
│       ├── decisionmatrix.mjs
│       └── precisioncalc.mjs
├── server.mjs              # local stdio MCP server (same engines + composites; AGENTSTACK_PROFILE env)
├── site/                   # landing page + mcp.json + llms.txt + _worker.js (built)
├── tests/composites.test.mjs
├── examples/agent_example.mjs
├── scripts/sync-engines.sh # re-vendor engines from the sibling repos
├── package.json · wrangler.toml · server.json · smithery.yaml · Dockerfile · LICENSE
└── README.md

Why vendor the engines? So this repo is self-contained and reproducible. The engines are the same deterministic modules that power the three standalone servers; npm run sync-engines re-copies them from the sibling repos when an upstream change lands.

Run it locally

bash

git clone <your-fork> agentstack-mcp && cd agentstack-mcp
npm install
npm test                      # composite-logic tests (no network)
npm run dev                   # -> http://127.0.0.1:8788/mcp
node examples/agent_example.mjs            # hosted demo
node examples/agent_example.mjs http://127.0.0.1:8788
node server.mjs               # dependency-light stdio server (AGENTSTACK_PROFILE=finance to subset)

Quick manual call:

bash

curl -s http://127.0.0.1:8788/mcp \
  -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"list_capabilities","arguments":{}}}'

Install via npm (stdio, no hosting)

Run the server locally over stdio with a single command — nothing to deploy:

bash

npx -y agentstack-mcp

Claude Desktop / any stdio MCP client (claude_desktop_config.json):

json

{ "mcpServers": { "agentstack": { "command": "npx", "args": ["-y", "agentstack-mcp"] } } }

This is the same deterministic engine as the hosted server, running on your machine.

Client configuration

Cursor — `~/.cursor/mcp.json`

json

{ "mcpServers": { "agentstack": { "url": "https://agentstack-mcp.pages.dev/mcp" } } }

Claude Desktop — `claude_desktop_config.json` (via `mcp-remote`)

json

{ "mcpServers": { "agentstack": { "command": "npx", "args": ["-y", "mcp-remote", "https://agentstack-mcp.pages.dev/mcp"] } } }

VS Code — `.vscode/mcp.json`

json

{ "servers": { "agentstack": { "type": "http", "url": "https://agentstack-mcp.pages.dev/mcp" } } }

Windsurf — `~/.codeium/windsurf/mcp_config.json`

json

{ "mcpServers": { "agentstack": { "serverUrl": "https://agentstack-mcp.pages.dev/mcp" } } }

Add "headers": { "X-API-Key": "ssak_live_..." } once you have a key.

Example composite payloads

Rank growth strategies on their projected outcomes:

json

{ "name": "evaluate_options_with_scenarios", "arguments": {
  "template": "saas_growth", "horizon": 12,
  "options": [
    { "name": "Aggressive", "inputs": { "new_customers_per_period": 60, "churn_rate": 0.05 } },
    { "name": "Lean",       "inputs": { "new_customers_per_period": 20, "churn_rate": 0.02 } }
  ],
  "criteria": [
    { "metric": "ending_mrr", "weight": 3, "direction": "benefit" },
    { "metric": "total_churned_customers", "weight": 1, "direction": "cost" }
  ]
} }

Value a plan's MRR stream:

json

{ "name": "plan_to_valuation", "arguments": {
  "template": "saas_growth", "horizon": 12,
  "inputs": { "new_customers_per_period": 60, "churn_rate": 0.05, "arpu": 60 },
  "cashflow_metric": "mrr", "rate": 0.01, "initial_investment": 150000
} }

Stress-test the decision:

json

{ "name": "stress_test_decision", "arguments": {
  "template": "saas_growth", "horizon": 12,
  "options": [ { "name": "Aggressive", "inputs": { "churn_rate": 0.05 } },
               { "name": "Lean", "inputs": { "churn_rate": 0.02 } } ],
  "criteria": [ { "metric": "ending_mrr", "weight": 3 } ],
  "stress": { "variable": "churn_rate", "variation": 0.5, "steps": 5 }
} }

Deploy on Cloudflare Pages

bash

npm install
npx wrangler login
npm run deploy      # esbuild -> site/_worker.js, then wrangler pages deploy

Runs fully free / private with no bindings or secrets (fails open on the free tier). For billing: bind a KV namespace AGENTSTACK_KV, set PRICE_STARTER / PRICE_PRO in [vars], and add Stripe secrets:

bash

wrangler pages secret put STRIPE_SECRET_KEY    --project-name agentstack-mcp
wrangler pages secret put STRIPE_WEBHOOK_SECRET --project-name agentstack-mcp

Routes: /mcp (Streamable HTTP), /checkout, /success, /portal, /webhook, /metrics.

Auth & rate limiting

Enforced in worker-src/billing.mjs: identify() reads X-API-Key / Authorization: Bearer and falls back to per-IP free tier; consumeQuota() is a KV daily counter (the single gating point). One key / one quota spans the whole stack. Marked NOTE (auth) / NOTE (rate limiting) seams show where to swap in JWT/mTLS or a token-bucket. None of it touches the deterministic math.

Relationship to the standalone servers

AgentStack is additive, not a replacement. The three products keep running on their own for single-domain use:

ScenarioSim — https://scenariosim-mcp.pages.dev/mcp
DecisionMatrix — https://decisionmatrix-mcp.pages.dev/mcp
PrecisionCalc — https://precisioncalc-mcp.pages.dev/mcp

License

MIT — see LICENSE.

Install

Tools (24)

list_capabilitieshealth_checksim_runsim_sensitivitysim_break_evensim_comparesim_list_templatesdecide

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "agentstack-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agentstack-mcp@1.0.1"
      ]
    }
  }
}

AgentStack MCP (Model Context Protocol Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

list_capabilities

health_check

sim_run

sim_sensitivity

sim_break_even

sim_compare

sim_list_templates

decide

decide_score

decide_sensitivity

decide_compare_two

decide_list_methods

calc_metric

calc_list_metrics

calc_currency_convert

calc_business_days

calc_compound_growth

calc_npv

calc_irr

calc_loan_amortization

calc_depreciation

plan_to_valuation

evaluate_options_with_scenarios

stress_test_decision

AgentStack MCP

🌐 Live hosted server (free, no install)

The three namespaces (24 tools)

Composite tools — the reason to use the stack

Profiles — fight tool-selection noise

Response envelope

Project structure

Run it locally

Install via npm (stdio, no hosting)

Client configuration

Cursor — ~/.cursor/mcp.json

Claude Desktop — claude_desktop_config.json (via mcp-remote)

VS Code — .vscode/mcp.json

Windsurf — ~/.codeium/windsurf/mcp_config.json

Example composite payloads

Deploy on Cloudflare Pages

Auth & rate limiting

Relationship to the standalone servers

License

Install

Related servers

Cursor — `~/.cursor/mcp.json`

Claude Desktop — `claude_desktop_config.json` (via `mcp-remote`)

VS Code — `.vscode/mcp.json`

Windsurf — `~/.codeium/windsurf/mcp_config.json`