Agentstack MCP server

Agentstack is a remote MCP server that gives an AI agent 24 tools, among them calc_business_days, calc_compound_growth, calc_currency_convert. It answers at https://agentstack-mcp.pages.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 22 October 2026, succeeded.

Status

Answering

Tools

Reliability

6 of 6 checks

Response time

121 ms

Transport

streamable HTTP

Last checked

22 October 2026

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

Description as the publisher wrote it.

The 24 tools Agentstack offers

Tool	What it does
`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. Inputs: operation, start_date, days, end_date, region, custom_holidays
`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. Inputs: operation, rate, years, present_value, future_value, begin_value
`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. Inputs: amount, from_currency, to_currency, date, live
`calc_depreciation`	COMPUTE. Asset depreciation schedule. method: straight_line \| declining_balance \| sum_of_years_digits. Inputs: method, cost, salvage_value, useful_life_years, currency
`calc_irr`	COMPUTE. Internal Rate of Return: per-period rate where NPV=0 (Newton + bisection). Requires a sign change in cashflows. Inputs: cashflows, guess
`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. Inputs: principal, annual_rate, term_months, extra_payment, currency, include_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 decima Inputs: metric, params, currency
`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). Inputs: rate, cashflows, currency
`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 Inputs: options, criteria, scores, method
`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. Inputs: option_a, option_b, options, criteria, scores, method
`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. Inputs: options, criteria, scores, method
`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. Inputs: options, criteria, scores, method, variation, steps
`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' ([{m Inputs: template, inputs, horizon, period_label, method, options
`health_check`	Aggregated health/status for the whole stack (all three engines + composites). No parameters.
`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.
`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 Inputs: template, inputs, metrics, horizon, period_label, cashflow_metric
`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'. Inputs: template, inputs, solve_for, target_metric, target_value, bounds
`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. Inputs: scenarios, compare_metric, goal, horizon, include_projections
`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- Inputs: template, inputs, metrics, horizon, period_label
`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'). Inputs: template, inputs, target_metric, variable, variables, variation
`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 eval Inputs: template, inputs, horizon, period_label, method, options

Add Agentstack to your AI client

Every block below points at https://agentstack-mcp.pages.dev/mcp. Pick your client and copy.

Claude Code: one command in your terminal

claude mcp add --transport http agentstack https://agentstack-mcp.pages.dev/mcp

Claude Desktop: claude_desktop_config.json

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

Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project

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

VS Code and GitHub Copilot: .vscode/mcp.json

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

Zed: Zed settings.json

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

Windsurf: ~/.codeium/mcp_config.json

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

JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON

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

Continue: .continue/mcpServers/neuronto.yaml

name: Agentstack
version: 0.0.1
schema: v1
mcpServers:
  - name: Agentstack
    type: streamable-http
    url: https://agentstack-mcp.pages.dev/mcp

Gemini CLI: ~/.gemini/settings.json

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

Codex CLI: MCP server config

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

Warp: MCP servers, + Add, paste JSON

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

Goose: a one-click extension link

goose://extension?url=https%3A%2F%2Fagentstack-mcp.pages.dev%2Fmcp&type=streamable_http&id=agentstack&name=Agentstack

Is Agentstack up right now?

It answered our last check on 22 October 2026 in 121 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Agentstack

Decisionmatrix6 tools Scenariosim6 tools Zentrik0 tools Hive Consult4 tools BuyAPI7 tools Radtask3 tools

Questions about Agentstack

How many tools does Agentstack have?

24, as returned by the server's own tools/list on 14 September 2026: calc_business_days, calc_compound_growth, calc_currency_convert, calc_depreciation, calc_irr, calc_list_metrics, calc_loan_amortization, calc_metric, and 16 more.

Is Agentstack down?

It answered our last check on 22 October 2026 in 121 ms. Over 6 checks since 11 September 2026 it answered 6.

How do I add Agentstack to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://agentstack-mcp.pages.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Agentstack need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: io.github.inity13. Endpoint host: agentstack-mcp.pages.dev. ARD identifier: urn:air:io.github.inity13:mcp:agentstack-mcp. First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.