Agentstack MCP is answering right now. Last checked 13 min ago. 27 installs a week from npm. It exposes 24 tools. Last commit 7 Oct 2026.
Deterministic reasoning stack for AI agents: simulate, decide & compute, plus cross-domain tools.
Installs per day
peak 15 · avg 5 · +17% w/w
a month agotoday
Uptime history
66 days of history · worst day 65%
66 days agonow
100.0%
Uptime 24h
91 of 91 checks
24
Tools
read from the server
43 ms
Response time
average over 24h
27
Installs / week
npm and PyPI
Nothing serious here today
Today is the operative word: we check Agentstack MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.
run in your terminal
claude mcp add agentstack-mcp --transport http https://agentstack-mcp.pages.dev/mcp~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"agentstack-mcp": {
"url": "https://agentstack-mcp.pages.dev/mcp"
}
}
}~/.codex/config.toml
[mcp_servers.agentstack-mcp]
url = "https://agentstack-mcp.pages.dev/mcp".cursor/mcp.json
{
"mcpServers": {
"agentstack-mcp": {
"url": "https://agentstack-mcp.pages.dev/mcp"
}
}
}.vscode/mcp.json
{
"mcpServers": {
"agentstack-mcp": {
"url": "https://agentstack-mcp.pages.dev/mcp"
}
}
}Available tools 24
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
calc
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_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_depreciation
COMPUTE. Asset depreciation schedule. method: straight_line | declining_balance | sum_of_years_digits.
calc_irr
COMPUTE. Internal Rate of Return: per-period rate where NPV=0 (Newton + bisection). Requires a sign change in cashflows.
calc_list_metrics
COMPUTE. List every supported metric with descriptions and required/optional params. No parameters.
calc_loan_amortization
COMPUTE. Level-payment loan: monthly payment, total interest, payoff, and (optional) full schedule.
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_npv
COMPUTE. Net Present Value (discounted cash flow). NPV = sum(CF_t/(1+rate)^t); cashflows[0] is period 0 (usually the negative outlay).
decide
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_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.
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.
sim
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.
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.
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').
capabilities
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.
evaluate
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.
health
health_check
Aggregated health/status for the whole stack (all three engines + composites). No parameters.
plan
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.
stress
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}.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://agentstack-mcp.pages.dev/mcp | streamable-http | answering | 64 ms | 13 min ago |
Alternatives to Agentstack MCP
same job, measured the same wayRosentic
by rosentic
Deterministic cross-branch conflict detection for AI coding agents
Agent Core
by kinbinghua-lgtm
Deterministic computation tools for AI agents. Zero dependencies, no network, read-only.
Agent Release Auditor
by veyndrasystems
Deterministic release gate for AI-written code and coding agents.
P
PackValue Tools
by umagestaointeligente
Six deterministic value tools for shopping and procurement agents.
Ariadne
by whyy9527
Deterministic local cross-service API-chain discovery for AI coding agents.
Flatland
by flatlandfi
Financial reasoning infrastructure for AI agents: typed models, deterministic compilation, receipts
Codelens MCP
by segentic-lab
Deterministic code maps for AI agents: 7 tree-sitter tools for TS/JS/Py — map, find, function_body
LingNao
by genesis-plan
LingNao: deterministic reasoning for AI agents → verified/refuted/unverifiable. ~3ms, fail-closed.
Agentstack MCP — questions
Answers built from our own checks of this server.
What can Agentstack MCP do?
It exposes 24 tools, read directly from the server on our last check. Among them: calc_business_days, calc_compound_growth, calc_currency_convert, calc_depreciation, calc_irr, calc_list_metrics and 18 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
What is Agentstack MCP mostly used for?
Its tools cluster around calc, sim and decide. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is Agentstack MCP working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 43 ms. The bar chart above shows every period we have measured.
How do I connect Agentstack MCP?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Agentstack MCP need an API key?
No. Agentstack MCP completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 24 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Agentstack MCP?
It answers our handshake in 43 ms on average, which is faster than 97% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Agentstack MCP?
The npm package agentstack-mcp was installed 27 times in the last week. Week over week that is +17%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Agentstack MCP open source?
Yes — it is published under the MIT licence, written in JavaScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.