Skip to main content
Glama
AgentStack MCP

AgentStack MCP

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)

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


Related MCP server: Sablier MCP Server

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

{ "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:

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

Example — plan_to_valuation (trimmed):

{
  "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

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

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:

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:

npx -y agentstack-mcp

Claude Desktop / any stdio MCP client (claude_desktop_config.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

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

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

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

VS Code — .vscode/mcp.json

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

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

{ "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:

{ "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:

{ "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

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:

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:

License

MIT — see LICENSE.

Available Tools

24 tools
calc_business_daysCInspect

COMPUTE. Business-day arithmetic with holidays.

Inputs: operation (required), start_date (required), days, region, +2 more.

calc_compound_growthDInspect

COMPUTE. future_value | present_value | cagr.

Inputs: operation (required), rate, years, currency, +5 more.

calc_currency_convertCInspect

COMPUTE. Convert currencies with Decimal precision.

Inputs: amount (required), to_currency (required), from_currency (required), date, +1 more.

calc_depreciationDInspect

COMPUTE. Depreciation schedule.

Inputs: cost (required), method (required), salvage_value (required), useful_life_years (required), +1 more.

calc_irrCInspect

COMPUTE. Internal Rate of Return.

Inputs: cashflows (required), guess.

calc_list_metricsBInspect

COMPUTE. List supported metrics + schemas.

Inputs: no named parameters.

calc_loan_amortizationCInspect

COMPUTE. Level-payment loan schedule.

Inputs: principal (required), annual_rate (required), term_months (required), currency, +2 more.

calc_metricCInspect

COMPUTE. Exact business/SaaS/finance metric (ltv, cac, rule_of_40, nrr, ...).

Inputs: metric (required), params (required), currency.

calc_npvCInspect

COMPUTE. Net Present Value.

Inputs: rate (required), cashflows (required), currency.

decideAInspect

DECIDE. Rank options against weighted criteria; returns winner, ranking, breakdowns, explanation.

Inputs: scores (required), options (required), criteria (required), method.

decide_compare_twoCInspect

DECIDE. Head-to-head between exactly two options.

Inputs: scores (required), criteria (required), method, options, +2 more.

decide_list_methodsBInspect

DECIDE. List scoring methods.

Inputs: no named parameters.

decide_scoreCInspect

DECIDE. Full normalized scored matrix + ranking.

Inputs: scores (required), options (required), criteria (required), method.

decide_sensitivityCInspect

DECIDE. Robustness of the winner to CRITERIA-WEIGHT changes.

Inputs: scores (required), options (required), criteria (required), steps, +2 more.

evaluate_options_with_scenariosCInspect

COMPOSITE (simulate -> decide). Project each option, rank the outcomes.

Inputs: options (required), criteria (required), inputs, method, +3 more.

health_checkBInspect

Aggregated health for the whole stack.

Inputs: no named parameters.

list_capabilitiesBInspect

Discovery: namespaces (sim_*, decide_*, calc_*), composite tools, and profiles.

Inputs: no named parameters.

plan_to_valuationCInspect

COMPOSITE (simulate -> compute). Project a scenario, value its cash-flow line (NPV/IRR).

Inputs: rate (required), template (required), cashflow_metric (required), inputs, +4 more.

sim_break_evenCInspect

SIMULATE. Solve for the input value that makes a metric hit a target.

Inputs: template (required), solve_for (required), target_value (required), bounds, +4 more.

sim_compareCInspect

SIMULATE. Compare 2-3 scenarios side by side.

Inputs: scenarios (required), goal, horizon, compare_metric.

sim_list_templatesAInspect

SIMULATE. List every scenario template with inputs and outputs.

Inputs: no named parameters.

sim_runCInspect

SIMULATE. Deterministic what-if projection from a template or free-form 'metrics' model.

Inputs: inputs, horizon, metrics, template, +1 more.

sim_sensitivityCInspect

SIMULATE. Vary scenario inputs and show impact on a target metric.

Inputs: template (required), steps, inputs, horizon, +5 more.

stress_test_decisionCInspect

COMPOSITE (simulate x decide). Stress a scenario assumption and see if the winner holds.

Inputs: stress (required), options (required), criteria (required), inputs, +4 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.5/5.0

    Scored across 24 tools

    Disambiguation4/5

    Most tools are cleanly separated by domain prefixes (sim_, decide_, calc_) with distinct actions. However, decide and decide_score have overlapping outputs, and calc_metric overlaps conceptually with specific calc_npv and calc_irr tools, creating potential confusion.

    Naming Consistency3/5

    Domain prefixes give structure, but the suffixes mix verbs and nouns inconsistently (sim_run vs sim_sensitivity, calc_metric vs calc_list_metrics). Composite tools use a completely different naming style, breaking the pattern.

    Tool Count3/5

    At 24 tools, the server is on the heavy side, but the three domains each justify several tools. Some redundancy (decide vs decide_score) could reduce the count, making it borderline.

    Completeness4/5

    Core workflows for simulation, decision, and calculation are well covered, including composite tools that span domains. Minor gaps exist, such as no way to create or edit scenario templates and no persistence for decisions, but these are not critical.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      An MCP server that provides deterministic, high-precision business, finance, and operational calculations such as SaaS metrics, currency conversion, business days, and financial formulas, returning structured JSON results.
      11
      41 npm
      MIT