firenum retirement planner
Server Details
When can you retire? A FIRE plan from your numbers, graded by Monte Carlo and every year since 1872.
- Status
- Healthy
- Uptime
- 100.0% over 22 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 1 tool
There is only a single tool, so there is no possibility of misselection between tools. All the described intents (retirement date, FIRE number, Coast/Barista/Lean/Fat FIRE, tax scenarios) are explicitly routed through this one entry point, and its description makes clear it is the sole action available.
The lone name, build_retirement_plan, follows a clear verb_noun snake_case convention that matches its domain precisely. No conflicting conventions exist to violate consistency.
A single tool is on the thin side for a domain as broad as retirement planning (plan creation, plan retrieval, scenario comparison), even though this tool is unusually parameter-rich and absorbs many sub-cases. It is defensible as a single-entry planner, but the surface feels minimal rather than well-scoped.
The tool covers the core lifecycle: producing a graded retirement answer, FIRE/Coast numbers, tax modeling, year-by-year tables, assumptions, and a plan link, with re-calls for alternate retirement years. Gaps exist around retrieving or updating an existing saved plan and comparing multiple scenarios side by side, which agents must work around by re-calling.
Available Tools
1 toolbuild_retirement_planBuild a retirement planARead-onlyInspect
Use when someone asks when they can retire, if their money will last, their FIRE number (the planner shows when they'd reach it), or about Coast, Barista, Lean or Fat FIRE, and gave numbers (age, income, savings, spending, debts). Send what they gave, as said. Returns its answer and plan link.
Turns what someone has said about their money into firenum's answer and their plan in firenum's Fire Planner
(FIRE: Financial Independence, Retire Early). The answer is the planner's own, as their plan shows it once
opened: when they can retire with their contributions, growth and inflation, graded three ways (average returns,
500 Monte Carlo simulations, every historical start year since 1872). For a FIRE number it gives the number and,
once it has their age, when they would reach it. All parameters are optional: with too little to grade,
missing says what to ask for.
Reply from answer. Give the headline with both counts: the headline's date is the first month the money lasts on
average returns, and the counts say how often that survives real market swings. When a count is under half, open
with that count ("The money lasts in only N of 500 simulated markets"), never with yes, even a qualified one ("on
average returns, yes", "a risky yes"): the date works on average but fails in most markets. coast_number is
their Coast FIRE number for coast_age (what they would need invested today to stop saving). coast is the
planner's own answer to stopping saving today: whether the money still lasts if they retire on the headline's date
and, if not, the date that works without more saving. assumed, when present, is what the answer took for
something they didn't say: say so in those terms. missing is what the planner needs before it can grade
anything: ask for it and call again. To grade another retirement year, call again with retire. Amounts are in
their currency, sums in today's money. table is their net worth year by year on each model, with income,
spending and withdrawals, and assumptions is what the answer rests on (the rates, how each model works, how
their numbers were read, what is not modeled): answer follow-ups from them (what they would have at 60, when the
money runs out in a bad market, why a date) without calling again, and say what an answer assumes when it matters.
Give them the returned url exactly as it is: it opens their quick-start with these numbers filled in, then the
whole plan (stress tests, a year-by-year table, where the money goes). Without source=agent the planner opens it
as a shared plan that saves nothing. It runs in their browser with no account, and nothing is saved until they
confirm: the link then becomes a new plan, "From a link", beside any plans they have. The plan keeps the accounts,
spending lines, debts, pension, Social Security and rental income sent. Salary and side income become one monthly
income.
Income is annual. Expenses and contributions are monthly. Amounts in whole currency units (not cents). Growth and inflation are percentages.
Taxes are off by default, in any country: income is take-home pay. For someone in the US who gives income before
tax, send taxes=us (and state, a partner, dependents, their Social Security statement figure and a Roth
conversion strategy when they say them): the planner then computes federal, state and payroll tax every year, and
the table gains each year's tax. Amounts are then dollars.
Before retirement, any spending, debt payments and contributions that income doesn't cover are paid from savings.
Without salary or side_income, and with retirement still ahead, the answer assumes an income that covers
spending, contributions and debt payments until then (assumed says so), and the quick-start asks for it.
| Name | Required | Description | Default |
|---|---|---|---|
| hsa | No | Health Savings Account balance. Default growth 7%. | |
| pia | No | Monthly Social Security benefit at full retirement age, from the SSA statement. The planner computes the benefit for claim_age from it. | |
| cash | No | Cash/checking balance. Default growth 0%. | |
| debt | No | Debt balance. | |
| food | No | Monthly food expense. | |
| roth | No | Roth account balance (Roth IRA, Roth 401k). Default growth 7%. | |
| birth | No | Birth year (YYYY). From an age, send the current year minus the age. Used with retire_age to compute retirement date. | |
| state | No | Two-letter US state code (DC too) for state income tax. Without it, federal tax only. | |
| taxes | No | "us" computes US federal, state and payroll tax every year (2026 law, carried forward with inflation). Income is then before tax and every amount is in dollars, whatever currency says. "off" (the default, any country) takes income as take-home pay. | off |
| crypto | No | Cryptocurrency balance. Default growth 0%. | |
| growth | No | Default portfolio growth rate (percentage). Retirement, Roth, brokerage and HSA balances follow it as the market rate (randomized in Monte Carlo, historical in backtests); it also overrides the fixed defaults of the other assets. | |
| retire | No | Target retirement year (YYYY). Takes precedence over retire_age. | |
| salary | No | Annual gross salary, as they said it (don't subtract tax). Grows 3%/year, stops at retirement (open-ended if no retirement date is given). The planner doesn't deduct taxes; if they gave a tax amount, include it in expenses. | |
| target | No | Accepted from older links and ignored. The planner answers with a retirement date, not a target. | |
| housing | No | Monthly housing expense (rent/mortgage). | |
| married | No | With a partner, files jointly. false files as two singles. | |
| pension | No | Annual pension income. Starts at retirement (immediately if no retirement date is given). | |
| savings | No | High-yield savings balance. Default growth 4.5%. | |
| currency | No | Display currency. All amounts should be in this currency. | USD |
| expenses | No | Total monthly spending. Send this alone, or categories alone. If both are sent, categories count as part of this total and only the remainder becomes "Monthly expenses" (never added on top). Do not repeat the total as a category. | |
| brokerage | No | Taxable brokerage account balance. Default growth 7%. | |
| claim_age | No | Age Social Security is claimed (62-70), for social_security (with birth) or pia. | |
| debt_name | No | Name/label for the debt. Default "Debt". | |
| debt_rate | No | Debt annual interest rate (percentage). | |
| inflation | No | Default inflation rate (percentage). Overrides individual expense defaults. | |
| insurance | No | Monthly insurance expense. | |
| utilities | No | Monthly utilities expense. | |
| dependents | No | Dependents' birth years (child tax credit until 17, ACA household size). | |
| healthcare | No | Monthly healthcare expense. | |
| retire_age | No | Target retirement age. Requires birth to compute retirement year. Ignored if retire is provided. | |
| retirement | No | Retirement account balance (401k, IRA, etc). Default growth 7%. | |
| real_estate | No | Real estate equity. Default growth 4%. | |
| side_income | No | Annual side hustle / freelance income. Stops at retirement (open-ended if no retirement date is given). | |
| debt_payment | No | Monthly debt payment. | |
| discretionary | No | Monthly discretionary spending. | |
| partner_birth | No | A partner's birth year (YYYY). The partner retires at the same time. Every account and income line stays the first person's. | |
| rental_income | No | Annual rental income. | |
| transportation | No | Monthly transportation expense. | |
| part_time_until | No | Age part_time_income stops (needs birth). Omitted or 100 = for life. | |
| roth_conversion | No | Roth conversion ladder from the first retired year, each December from traditional accounts into Roth. fill_12 converts up to the top of the 12% bracket; fixed converts roth_conversion_amount a year; aca stays under the ACA premium credit's income limit. | none |
| social_security | No | Annual Social Security income. Starts at claim_age when sent with birth; otherwise at the later of retirement and age 67 (uses whichever is known; immediately if neither). | |
| hsa_contribution | No | Monthly HSA contribution. | |
| part_time_income | No | Annual part-time income in retirement (Barista FIRE). Starts at the retirement date and runs on; with no retirement date given, the plan retires at the earliest date that works with this income. | |
| cash_contribution | No | Monthly cash contribution. | |
| roth_contribution | No | Monthly Roth account contribution. | |
| crypto_contribution | No | Monthly crypto contribution. | |
| savings_contribution | No | Monthly savings contribution. | |
| roth_conversion_until | No | Age the conversions stop. | |
| brokerage_contribution | No | Monthly brokerage contribution. | |
| roth_conversion_amount | No | Dollars a year, with roth_conversion=fixed. | |
| retirement_contribution | No | Monthly retirement account contribution. | |
| real_estate_contribution | No | Monthly real estate contribution (e.g., extra mortgage principal). |
Output Schema
| Name | Required | Description |
|---|---|---|
| url | Yes | Full URL to open the Fire Planner with pre-populated data. |
| answer | No | The planner's answer, in its words, as their plan shows it once opened (average returns, today's money, their currency). A field that does not apply is left out. The whole answer is left out once the day's answers are used up (a limit shared by every caller, reset at 00:00 UTC): the link still opens their plan. |
| params_applied | Yes | List of parameter names that were recognized and applied. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint true, openWorldHint false, and destructiveHint false. The description goes much further: it explains the return format (answer, coast_number, coast, assumed, missing, table, assumptions), the plan link behavior (shared plan saves nothing, runs in browser, nothing saved until confirm), tax handling, and pre-retirement cash-flow assumptions. This is rich behavioral context beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is long but justified for a 52-parameter tool. It is front-loaded with usage and purpose, though some repetition about `missing` and tax defaults could be trimmed. The paragraph-based structure is dense but mostly earns its place given the tool's complexity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity, the description covers purpose, usage, behavioral details, units, tax modes, plan-link behavior, and return fields. The output schema exists, but the description still explains how to interpret the answer and plan link, making it complete for an agent to call and use the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents every parameter. The description adds cross-cutting semantics: income is annual, expenses and contributions are monthly, amounts are in whole currency units, growth and inflation are percentages, and taxes default to off. It also clarifies how `missing` and `assumed` work, which adds useful meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: it turns what someone has said about their money into firenum's answer and their plan. It clearly covers retirement timing, money lasting, FIRE number, and Coast/Barista/Lean/Fat FIRE variants. The scope is unambiguous even without sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives explicit when-to-use conditions ('Use when someone asks when they can retire...') and notes that all parameters are optional, with `missing` indicating what to ask for. It also says to call again with `retire` to grade another year. It lacks explicit when-not-to-use guidance, but for a single-tool context the usage is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Changed
build_retirement_plan1 field changed- added
Input schema / properties / part_time_untilAdded value: +{ + "description": "Age part_time_income stops (needs birth). Omitted or 100 = for life.", + "example": 60, + "maximum": 100, + "minimum": 30, + "type": "integer" +}
1 tool update
- Changed
build_retirement_plan2 fields changed- changed
Input schema / properties / claim_age / descriptionPrevious value: -"Age Social Security is claimed (62-70), with pia."New value: +"Age Social Security is claimed (62-70), for social_security (with birth) or pia." - changed
Input schema / properties / social_security / descriptionPrevious value: -"Annual Social Security income. Starts at the later of retirement and age 67 (uses whichever is known; immediately if neither)."New value: +"Annual Social Security income. Starts at claim_age when sent with birth; otherwise at the later of retirement and age 67 (uses whichever is known; immediately if neither)."
1 tool update
- Changed
build_retirement_plan1 field changed- changed
Output schema / properties / answer / properties / assumptions / properties / income / descriptionPrevious value: -"Each income: its amount, its frequency (monthly, annual, one-time), from (now or YYYY-MM) and until (retirement, never or YYYY-MM), growth."New value: +"Each income: its amount, its frequency (monthly, annual, one-time), from (now, retirement or YYYY-MM) and until (retirement, never or YYYY-MM), growth."
1 tool update
- Changed
build_retirement_plan12 fields changed- added
Input schema / properties / claim_ageAdded value: +{ + "default": 67, + "description": "Age Social Security is claimed (62-70), with pia.", + "maximum": 70, + "minimum": 62, + "type": "integer" +} - added
Input schema / properties / dependentsAdded value: +{ + "description": "Dependents' birth years (child tax credit until 17, ACA household size).", + "example": [ + 2015, + 2018 + ], + "items": { + "type": "integer" + }, + "type": "array" +} - added
Input schema / properties / marriedAdded value: +{ + "default": true, + "description": "With a partner, files jointly. false files as two singles.", + "type": "boolean" +} - added
Input schema / properties / partner_birthAdded value: +{ + "description": "A partner's birth year (YYYY). The partner retires at the same time. Every account and income line stays the first person's.", + "example": 1988, + "type": "integer" +} - added
Input schema / properties / piaAdded value: +{ + "description": "Monthly Social Security benefit at full retirement age, from the SSA statement. The planner computes the benefit for claim_age from it.", + "example": 2400, + "type": "number" +} - added
Input schema / properties / roth_conversionAdded value: +{ + "default": "none", + "description": "Roth conversion ladder from the first retired year, each December from traditional accounts into Roth. fill_12 converts up to the top of the 12% bracket; fixed converts roth_conversion_amount a year; aca stays under the ACA premium credit's income limit.", + "enum": [ + "none", + "fill_10", + "fill_12", + "fill_22", + "fill_24", + "fixed", + "aca" + ], + "type": "string" +} - added
Input schema / properties / roth_conversion_amountAdded value: +{ + "description": "Dollars a year, with roth_conversion=fixed.", + "example": 30000, + "type": "number" +} - added
Input schema / properties / roth_conversion_untilAdded value: +{ + "default": 72, + "description": "Age the conversions stop.", + "type": "integer" +} - added
Input schema / properties / stateAdded value: +{ + "description": "Two-letter US state code (DC too) for state income tax. Without it, federal tax only.", + "example": "CA", + "type": "string" +} - added
Input schema / properties / taxesAdded value: +{ + "default": "off", + "description": "\"us\" computes US federal, state and payroll tax every year (2026 law, carried forward with inflation). Income is then before tax and every amount is in dollars, whatever currency says. \"off\" (the default, any country) takes income as take-home pay.", + "enum": [ + "us", + "off" + ], + "type": "string" +} - added
Output schema / properties / answer / properties / assumptions / properties / taxesAdded value: +{ + "description": "Off (income is take-home pay), or what US taxes on computes with: the state, filing, dependents and the Roth conversion strategy.", + "type": "string" +} - changed
Output schema / properties / answer / properties / table / descriptionPrevious value: -"Year by year in today's money, the rows and numbers the planner's Table shows (3 significant figures): the first and last years, every 5th year and the retirement year. Net worth is at the end of each year: on average returns, and the 10th percentile, median and 90th percentile of the Monte Carlo simulations and of the backtest's start years, for each model that ran (0 once the money has run out). Income, spending (debt payments not included) and withdrawals are on the average path. `notes` names a part first year and the years that draw on a retirement account while the early withdrawal penalty applies."New value: +"Year by year in today's money, the rows and numbers the planner's Table shows (3 significant figures): the first and last years, every 5th year and the retirement year. Net worth is at the end of each year: on average returns, and the 10th percentile, median and 90th percentile of the Monte Carlo simulations and of the backtest's start years, for each model that ran (0 once the money has run out). Income, spending (debt payments not included) and withdrawals are on the average path. `notes` names a part first year and the years that draw on a retirement account while the early withdrawal penalty applies. With taxes=us, `tax` is the year's federal, state and payroll tax and `tax_rate_pct` its share of the year's income and withdrawals."
1 tool update
- First observed
build_retirement_plan
Publisher details
- Operator
- firenum LLC · Publisher source
- Operator website
- https://firenum.com · Publisher source
- Vendor relationship
- First-party · Publisher source
- Documentation
- https://firenum.com/developers#mcp · Publisher source
- Trust center
- https://firenum.com/privacy · Publisher source
- Restrictions
- No restrictions · Publisher source
Related MCP Connectors
Retirement Monte Carlo, tax-aware withdrawals, 2026 tax calculators, RMD, IRMAA, every-state tax.
Deterministic US financial planning: retirement Monte Carlo, Roth conversion, RMD, tax, IRMAA, SS
FIRE & retirement calculators + a multi-currency portfolio rebalancer (exact buy/sell trades).
Compound interest and Monte Carlo simulators for investing, retirement and past asset returns.
Related MCP Servers
FlicenseNot gradedqualityDmaintenanceTax-aware retirement planning for Canada and the US. CPP/OAS and Social Security timing, RRSP/TFSA/401k/IRA projections, Monte Carlo simulation, withdrawal order optimization, and historical backtesting against 150 years of market data.2-- AlicenseNot gradedqualityBmaintenanceRuns Monte Carlo retirement projections on the hosted QuantCalc engine, returning success rates, portfolio distributions, and the assumptions behind every number.MIT
- FlicenseNot gradedqualityDmaintenanceEnables institutional-grade Monte Carlo risk analysis for portfolios, startups, real estate, and betting strategies using fat-tail distributions and proprietary algorithms. Provides comprehensive risk metrics including CVaR, VaR, ruin probability, and survival probability across multiple asset classes.1-
- AlicenseNot gradedqualityBmaintenanceEnables users to run stochastic cash runway simulations, estimate ruin probability and low-percentile wealth, and compute safe discretionary spending caps and emergency liquidity buffers.7MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.