Planners About

MCP Changelog & Version History

What changed on mcp.digitalcalculator.info/mcp, newest release first. Each line says whether the release was Breaking, Additive or a Fix; open it for what changed in your requests and responses. The rules for how we change things, and the dated list of announced changes, are in the Versioning & Deprecation Contract.

Current version

The endpoint has three independent version numbers, each covering a different surface:

  • Contract version — serverInfo.version in the initialize response. It versions the tool contract (tool names, inputs, outputs, envelope), and it is the version the releases below are numbered by. Read it from the endpoint rather than from this page: it always names what the server is running.
  • npm shim version (@markcolabs/mcp, currently 0.4.3) — versions the optional stdio adapter only. A shim release does not imply a contract change, and a contract release does not need a new shim.
  • Engine version (engine_version, in every result) — versions the math behind one tool, and moves when that tool’s formula changes.

The protocolVersion in the initialize response is not one of them: it is the MCP specification revision your client and the server agreed to speak (2026-07-28, 2025-11-25 or 2025-06-18).

Release history

Breaking: a call that worked before may need a change. Additive: new tools, inputs, fields or resources; existing calls are answered as before. Fix: a correction; the release says which figures move.

2.12.0 · 2026-11-13 · Additive — tools accept rule_year 2027; new compare_tax_years tool

Without rule_year, every tool computes exactly as before, on the 2026 rules. With rule_year: 2027, evaluate_roth_conversion uses the 2027 federal tax brackets (IRS Rev. Proc. 2026-35); check_contribution_eligibility uses the 2027 HSA limits (Rev. Proc. 2026-24) and the 2027 401(k) and IRA limits and income phase-outs (IRS Notice 2026-66, published November 12, 2026); and plan_retirement_income runs its accumulation module on the 2027 401(k) and annual additions limits and its Social Security and RMD modules on SSA’s 2027 figures. A 2027 call that needs a figure the server does not hold returns a BUSINESS_RULE error on rule_year that names it, never a 2026 figure under a 2027 label. A 2026 401(k), IRA or HSA answer says the 2027 figures are published and how to get them. New resources: dc://irs/limits/2027, dc://ssa/bend-points/2027, and their rule-year diffs. paycheck_net_pay stays on 2026 until the IRS publishes the 2027 withholding tables.

New tool, compare_tax_years: what changes from 2026 to 2027 for one person’s age, filing status and accounts, each figure with its IRS or SSA source, the deadlines that apply, and what is not published yet; the same answer as the What Changes for You page.

Compatibility: MINOR — rule_year now also accepts 2027, with five new resources and one new tool. No existing output field changes, and no call without rule_year moves.

2.11.1 · 2026-11-09 · Fix — the 401(k) and IRA result views carry the IRS’s 2027 tax tables

The IRS published its 2027 inflation adjustments on November 5, 2026 (Rev. Proc. 2026-35). The site’s tax record now holds the 2027 federal income tax brackets, standard deduction and long-term capital gains thresholds in place of projections, and the 401(k) and IRA views are built from that record, so their resource addresses change to ui://digitalcalculator/retirement-401k-result-78a9d85e and ui://digitalcalculator/ira-result-c8c1ac72. An address with an earlier hash still resolves. Every tool still computes on the 2026 rules (rule_year 2026), so no result changes. Also in this release: the reader summary shows a rate under 0.1% as entered (0.075%, not 0.08%), and parallel calls beyond the endpoint’s rate are answered with 429 (rate limited) instead of 503.

Compatibility: PATCH — the two views’ HTML and one summary sentence change; no input, output or resource field changes, and no figure a tool returns moves.

2.11.0 · 2026-10-21 · Additive — new net_worth_percentile tool; the Social Security estimate names its earnings assumption

The new net_worth_percentile tool ranks a U.S. family’s net worth against the Federal Reserve’s 2025 Survey of Consumer Finances, the same way the net worth percentiles page does: among families around the same age (from an optional birth_year), the Fed’s age group, an income group and an education group, each with a 95% likely range, plus the next milestones, a timeline to the next one, and how the same net worth ranked in 2022. Where the Fed’s report publishes a group median (all families and the six age groups), the tool quotes the report’s figure and says so in peer_median_basis. Its data is a new resource, dc://scf/2025/networth-percentiles.

plan_retirement_income’s social_security module now lists the factor it has always used, career-average earnings of 65% of annual_salary, as assumptions.career_average_factor (marked fixed: true: no input changes it), and its methodology.url points at the Social Security or RMD methodology page when the 401(k) module is not selected. The interactive views for the home scenario, loans, growth and emergency funds, not yet served by the hosted endpoint, gain an “Open full scenario” button: it opens the matching calculator on this site with the scenario filled in, carried in the part of the link after the #, which browsers do not send to the server with the page request. It appears only when the host can open links and the calculator page shows the same figure for that scenario.

Compatibility: MINOR — a new tool and a new resource; one new entry in assumptions and a module-matched methodology.url on plan_retirement_income. No existing figure, input or output field changes.

2.10.1 · 2026-10-14 · Fix — Social Security uses SSA’s 2027 figures

SSA announced them on October 14, 2026: a 3.6% cost-of-living adjustment effective December 2026, a 2027 taxable maximum of $192,300 (it was a projection, $192,000), 2027 bend points of $1,340 and $8,077, and a 2025 national average wage index of $72,800.33. plan_retirement_income’s social_security module (and the legacy social-security REST alias) adds the new COLA for anyone who turned 62 in 2026 or earlier, so those estimates are in 2027 dollars, and uses the 2027 bend points for anyone turning 62 in 2027 or later. A worker born in 1960 who earned the taxable maximum every year gets SSA’s published 2027 maximum at full retirement age, $4,188 ($4,188.20). dc://ssa/bend-points/2026 carries the new rows. The Social Security calculator uses the same record.

Compatibility: PATCH — no input, output field or resource field changes; Social Security figures move.

2.10.0 · 2026-10-06 · Fix — a shared allowance for Claude’s connectors, 2026-07-28 request checks, and two rounding corrections

Calls through Claude’s connectors get their own allowance. Anonymous calls from Anthropic’s published outbound address range (160.79.104.0/21, which Claude uses for connector calls) now share one allowance of 150 calls per 5 minutes and 5,000 per UTC day, instead of 30 and 500 for each address; other addresses keep 30 and 500, and calls with a key are unaffected.

Requests in the 2026-07-28 envelope are checked. A request whose params._meta carries io.modelcontextprotocol/protocolVersion now gets protocol revision 2026-07-28’s request checks: a malformed envelope is HTTP 400 with -32602; a missing or disagreeing MCP-Protocol-Version, Mcp-Method or Mcp-Name header is HTTP 400 with -32020; a revision the server does not serve is HTTP 400 with -32022; an unknown method is HTTP 404.

Half a cent rounds up. An amount that falls exactly on half a cent now rounds up (away from zero) in every tool, and long daily-compounding projections at very low rates are computed without losing digits. A small share of results move by one cent: a $246,489 loan at 0% over 10 years is $2,054.08 a month, not $2,054.07. A reduced Roth IRA limit rounds up: in check_contribution_eligibility, a Roth limit reduced by the income phase-out now rounds up to the next multiple of $10, as IRS Publication 590-A’s worksheet does, instead of to the nearest $10; a single filer age 40 with MAGI $160,496 can contribute $3,760, not $3,750. A limit already on a multiple of $10 and the $200 minimum are unchanged.

Compatibility: MINOR — no tool input or output field changes. A request without that envelope key, including those from clients that connect with initialize, is answered exactly as before.

2.9.0 · 2026-10-06 · Fix — requests from other websites are refused, and request bodies must be JSON

A request carrying an Origin header other than https://www.digitalcalculator.info now gets HTTP 403 on every route, as the MCP Streamable HTTP specification requires to prevent DNS rebinding. A request body not declared as Content-Type: application/json gets HTTP 415. On /mcp both are a JSON-RPC error with code -32600 and no id; on the REST routes they use the usual error envelope. A free key from POST /v1/keys/public now comes with a private claimToken, and POST /v1/keys/claim requires it for a dc_pub_ key, because that key is meant to be published.

Compatibility: MINOR — no tool input, output field or figure changes. MCP hosts, SDKs, server-side code and curl send no Origin and already declare JSON, so they see no difference; the bodyless key-mint call needs no Content-Type. A free key created before this release cannot be claimed (create a new one, or email us).

2.8.0 · 2026-10-05 · Fix — the Social Security estimate is wage-indexed

plan_retirement_income’s social_security module (and the legacy social-security REST alias) indexes the modeled earnings history to national wage growth with SSA’s average wage index: each career year is capped at that year’s wage base and indexed to the year the worker turns 60, and the highest 35 years count. A worker born in 1959 who earned the taxable maximum every year now gets SSA’s published $4,152 at full retirement age ($4,152.40; it was $4,234.40). dc://ssa/bend-points adds the wage-index series (awi_by_year, awi_published_through, awi_scope) and wage bases from 1951. The Social Security calculator uses the same code.

Compatibility: MINOR — additive resource fields; no input or output field changes. Figures move only where a salary reaches a year’s cap, almost always down (median about 2% where they move). The tool’s engineVersion moves from 2.0.0 to 3.0.0.

2.7.0 · 2026-10-04 · Fix — the Roth break-even compares like with like

evaluate_roth_conversion’s break_even_years is now the first whole year, within the new optional horizon_years (default 20), in which converting is at least even with not converting: the Roth balance against the Traditional balance after tax at the retirement rate, plus the conversion tax kept invested at the same return. Otherwise it is null. At constant rates that is 0 when the retirement rate is at or above the conversion’s effective rate, and null when it is below. The earlier log-ratio estimate compared the retirement rate with the marginal rate and could report a break-even of a few years where converting never caught up. The Roth conversion calculator uses the same rule from the same code.

Compatibility: MINOR — a new optional input with a documented default; break_even_years keeps its name and type but changes meaning, and break_even_note is reworded. The tax, marginal and effective rates and the 5-year-rule flag do not change. The tool’s engineVersion moves from 1.2.0 to 2.0.0.

2.6.0 · 2026-09-29 · Additive — an estimate of the first required minimum distribution

plan_retirement_income called with both accumulation and rmd, before required minimum distributions start, adds modules.rmd.first_rmd_estimate: the projected balance at retirement carried at the same return to December 31 of the year before the first RMD year, divided by the Uniform Lifetime Table period for the age reached that year, with the method in a note. On the hosted endpoint from 2026-10-04.

Compatibility: MINOR — one new output object, present only for that pairing of modules before RMDs start; no input or existing figure changes. The tool’s engineVersion moves from 1.0.0 to 1.1.0.

2.5.0 · 2026-09-29 · Additive — out-of-range arguments are named in the answer

An argument answered although it is outside its documented range adds a warnings[] entry with code: "input_out_of_range" naming the argument, the value and the accepted range. Today only paycheck_net_pay’s legacy dependents (documented 0 to 20, whole numbers) reaches it; every other documented range is already refused. The dependents description carries the notice. On the hosted endpoint from 2026-10-04.

Compatibility: MINOR — one new warning entry, present only for an out-of-range argument; no input, output field or figure changes. Refusing the warned values is a later MAJOR change, announced under Upcoming changes for no earlier than 2027-05-27.

2.4.0 · 2026-09-28 · Additive — answers say when their IRS figures may be out of date

check_contribution_eligibility and plan_retirement_income (with the accumulation module) add a warnings[] entry with field: "rule_year": rule_year_newer_published when the IRS has published a newer year’s figures that this server does not apply yet (today, the 2027 HSA limits on kind: "hsa" answers), and rule_year_past_review once the rule year’s figures pass their review date. The IRS limit figures behind these tools also moved to a single shared record used by both this server and the website’s calculators; no value changed. On the hosted endpoint from 2026-10-04.

Compatibility: MINOR — one new, optional-to-read warning entry, present only when there is something to say; no input, output field or figure changes. The 401(k) and IRA result views are re-published at new content-hashed URIs (their bundled code was re-laid out, not changed); the old URIs still resolve.

2.3.0 · 2026-09-28 · Fix — the Form W-4 Step 3 dependent credit, split by kind

paycheck_net_pay applied one flat $2,000 per dependents, at every income. Form W-4 (2026) Step 3 has two amounts — $2,200 per qualifying child under 17, $500 per other dependent — and applies only when total income is at or below $200,000 ($400,000 married filing jointly). The tool now takes optional children_under_17 and other_dependents (each 0–20); the legacy dependents still works, read as qualifying children under 17, and a new dependent_credit_status field (applied, none_claimed, or income_above_limit) says what happened. Sending dependents together with either new count is refused rather than guessed. When the legacy field is what moved the credit, the new dependents_reading_note field says it was read as qualifying children under 17 (null otherwise). The paycheck engineVersion moves to 2.1.0. On the hosted endpoint from 2026-10-04.

Compatibility: MINOR — two new optional inputs and two new output fields; every call that worked before still works. A call without dependents, or with dependents: 0, keeps every figure. A call with a non-zero dependents now gets the form’s per-child amount, and above $200,000/$400,000 income correctly reports no credit, where the flat pre-2.3.0 rule applied one anyway.

2.2.0 · 2026-09-28 · Fix — the RMD start age for people born July 1949 through 1950

plan_retirement_income’s rmd module gave a start age of 70½ for everyone born in 1950 or earlier. Under the SECURE Act of 2019, anyone who reached 70½ after December 31, 2019 — born on or after July 1, 1949 — starts at 72, so the module now reports 72 and the matching first RMD year for births from July 1949 through 1950 (born 1950: 72 and 2022, where it gave 70½ and 2021). Birth year alone cannot split 1949, so the tool takes a new optional birth_month (1–12). Without it, a birth in 1949 or earlier is read as the first half of the year, which gives the earlier start age and first RMD year, and assumptions.birth_month says so. The RMD amount itself does not change: everyone affected is past both ages. The RMD calculator applies the same rule with the birth month it already asks for. On the hosted endpoint from 2026-10-04.

Compatibility: MINOR — one optional input; every call that worked before still works. The start age and first RMD year move only for births in 1950 or earlier (a correction toward the statute); births from 1951 on are unchanged, and so is every RMD amount.

2.1.0 · 2026-09-27 · Fix — project_growth reads an APY; the 401(k) projection applies the 415(c) limit

(a) project_growth takes rate_type. Omitted or nominal, the rate compounds at compounding_frequency as before, the compound interest calculator’s convention. apy reads it as an annual percentage yield, the rate a bank advertises, and runs the savings calculator’s formula. Before this release an APY passed to the tool was read as nominal and overstated the balance: $10,000 plus $500 a month at 5% for 10 years gave $94,111.23, where the savings calculator gives $93,470.53. With rate_type: "apy" the tool now gives $93,470.53. When the default is applied, assumptions says so. (b) plan_retirement_income’s accumulation module applies the IRC 415(c) limit on total annual additions (employee plus employer, with any catch-up on top), taking the excess off the employer match, and adds annual_additions_note when it binds. The 401(k) calculator already applied it, so for a $500,000 salary with a 20% deferral and a 100% match up to 10%, age 45 to 65 at 7% with catch-up, the module gave $3,293,789.30 and now gives the calculator’s $3,191,300.57. (c) emergency_fund_recommendation’s description no longer describes a difference from the site’s methodology that no longer exists: the tool and the calculator run one engine. (d) The interactive views follow: the mortgage view reads the snake_case argument names, the 401(k) view (and the embeddable 401(k) widget, which shares it) applies the 415(c) limit, and the earlier project_growth view shows a notice for an APY result rather than a nominal card. On the hosted endpoint from 2026-10-04.

Compatibility: MINOR — one optional input and two output fields; every call that worked before still works. Without rate_type, project_growth figures are unchanged. The 415(c) cap is a correction toward the statute: it moves only high-salary, large-match accumulation projections, and always downward; typical projections do not move.

2.0.0 · 2026-09-26 · Breaking — paycheck_net_pay stops computing state income tax, for every state

The state figure for the 41 states and DC that tax wages came from one effective rate per income tier, and where it could be checked against a full bracket calculation it differed by up to 87%, in both directions. The $0 for the 9 states with no tax on wage income is not a complete state deduction either (Washington, for example, withholds WA Cares and paid-family-leave premiums). So, for every state, unless you pass the new optional argument state_local_tax_annual: state_tax, state_tax_annual, state_effective_rate_percent, state_tax_source and no_state_income_tax are null, a new state_tax_status field reads not_provided, state_tax_notes says state and local taxes are not included, and net pay is after federal tax and FICA only. state_local_tax_annual (USD per year, no default) takes your own state and local tax and uses it exactly, for any state (state_tax_status: "user_supplied"). state is still accepted and validated, and changes no figure. The paycheck engineVersion moves to 2.0.0. On the hosted endpoint from 2026-09-27. See paycheck_net_pay.

Compatibility: MAJOR — five output fields that were always numbers or booleans may now be null, which the versioning rules class as breaking. Nothing is removed or renamed and every call that worked before still works; net pay for a state that taxes wages rises by the estimate that is no longer deducted, and federal and FICA figures are unchanged. The 90-day notice window was waived, and is disclosed here and on the contract page: the release withdraws a state-tax figure that could be materially wrong on a tax question, and keeping it published for the notice period was the greater risk (decided 2026-09-26). Check state_tax_status before reading state_tax as a number. The input schema adds the new argument, the output schema adds state_tax_status and marks the five fields nullable.

1.11.0 · 2026-09-26 · Additive — growth and emergency-fund views, and a call counter

(a) emergency_fund_recommendation gains a ui:// view: the target, a progress ring of the savings so far against it with the time to the goal in words, and the month-by-month savings balance against the target, with sliders that recompute in the view. (b) project_growth’s view is rebuilt as a stacked area of the money put in and the growth on it, year by year, with the year growth overtakes the money put in marked. Both share a settled scenario with the assistant the same way as the 1.10.0 views, and say so on screen. Neither is served by the hosted endpoint yet; it keeps its earlier views. (c) recompute_scenario also accepts emergency_fund_recommendation. (d) The server counts calls per tool per day: each call records the tool name and the date, and nothing else — no arguments, results or caller details.

Compatibility: MINOR — a view on a tool that had none, and one more value in recompute_scenario’s tool list; no tool result or argument changes, and tool results are the same on both endpoints. The earlier growth view URI keeps resolving.

1.10.0 · 2026-09-26 · Additive — the interactive home scenario

(a) One view now serves both mortgage_monthly_payment and evaluate_affordability, so evaluate_affordability gains a ui:// view (_meta.ui.resourceUri and _meta["openai/outputTemplate"]). It shows the payment or the maximum home price, a year-by-year repayment chart with the previous scenario drawn as a dashed line, the front-end and back-end debt-to-income ratios against their targets (in words as well as on a gauge), and sliders that recompute in the view with the same calculation module the server runs. When you stop adjusting for 1.5 seconds, the view tells the assistant which scenario you settled on, and it says so on screen; a Use this scenario button shares it at once. Where the host offers it, a full-screen mode compares up to four pinned scenarios. (b) loan_monthly_payment’s view is rebuilt the same way. (c) Both views read only the v2 (snake_case) keys, so the scheduled removal of the camelCase names cannot break them. Neither is served by the hosted endpoint yet; it keeps its earlier views until they move there.

Compatibility: MINOR — a view on a tool that had none; no tool result, argument or schema changes. Tool results are the same on both endpoints. The earlier mortgage and loan view URIs keep resolving.

1.9.0 · 2026-09-26 · Additive — the foundation for interactive result views (MCP Apps)

(a) One app-only tool, recompute_scenario: { tool, arguments } returns exactly what calling tool with arguments returns. It is listed with _meta.ui.visibility: ["app"] so an MCP Apps host keeps it from the model; an interactive view calls it only when it cannot compute a changed scenario itself (a view built against an older engine, or a rule year it does not carry). Models should call the calculators directly, and it is not counted in the anonymous tool count. (b) Content-hashed view URIs: each ui:// view is linked and listed at ui://digitalcalculator/<view>-<hash>, where the hash is taken over the view’s HTML, so a host that caches views by URI picks up a changed view; resources/read answers any hash of a known view, and the earlier fixed URIs, with the current view. (c) The mortgage, loan and affordability tools now compute through one shared module per tool that the interactive views also run, so a figure a view shows is the figure the server returns. On the hosted endpoint from 2026-09-27. See recompute_scenario and View URIs.

Compatibility: MINOR — one new tool and new view URIs; every existing tool, argument, key and value is unchanged, including every result of the three tools moved onto the shared modules. tools/list adds recompute_scenario only. The five existing views are the same documents at new URIs; their old URIs keep working.

1.8.0 · 2026-09-25 · Additive — one naming convention for results: the v2 envelope

Every success envelope of the ten anonymous tools — on tools/call and on each tool’s REST twin — gains, beside the keys it already had: (a) a snake_case twin of every camelCase key, at every depth (monthly_payment beside monthlyPayment; modules.accumulation.year_by_year beside yearByYear); (b) a *_percent field for every rate or ratio, as a whole-number percent — the decimals become percents rounded to 2 decimals (marginal_rate_on_conversion_percent: 22 beside marginalRateOnConversion: 0.22; state_effective_rate_percent beside stateEffectiveRate), computed percents are rounded to 2 decimals (savings_rate_percent: 33.65), and a percent that echoes your own argument keeps your exact value; (c) notes that name arguments the way the schema does (traditional_deduction_note says workplace_coverage), and an argument on every unit warning; (d) calculated_at, engine_version, an inputs echo of the arguments the result was computed from (snake_case, after aliases and defaults — send it back and you get the same result) and defaulted_inputs, naming the ones that came from a default. The output schemas declare every new field and mark the camelCase properties deprecated; tool descriptions name the new keys. The 17 camelCase argument spellings stay accepted, now with the removal rule in their descriptions and in the _meta deprecation marker. On the hosted endpoint from 2026-09-27. See The v2 envelope.

Compatibility: MINOR — every existing key keeps its name and value byte-for-byte, every accepted argument is still accepted, and no figure moves; the output schemas only add properties (the twins, inputs, defaulted_inputs) and deprecated flags. The legacy REST-only aliases are unchanged. Scheduled removal: the camelCase argument spellings and the camelCase/decimal output keys will be removed in a MAJOR release under the contract’s notice rules, which set the earliest date.

1.7.0 · 2026-09-25 · Additive — citations you can click, and a result a model can read

(a) https source links: every success envelope gains source_links[] — one { uri, url } pair per sources[] entry, where url is the public page that shows the same figures — and every provenance[] record gains the same url beside its uri. Where no page shows a resource (the methodology manifest, or a rule year the site does not publish), the link is the tool’s methodology page; see https source links. (b) The content summary: a request that sends MCP-Protocol-Version 2025-06-18 or later gets a short plain-text summary in content[0].text — key figures (currency to the cent, percentages to at most two decimals), notes with argument names spelled as the schema spells them, applied assumptions, unit warnings, methodology and source links, and the disclaimer — instead of the serialized envelope; structuredContent keeps everything, including year-by-year series. For plan_retirement_income the text a model reads falls from about 9 KB to about 3.5 KB. A request without the header keeps the serialized envelope, and _meta["info.digitalcalculator/contentFormat"] ("summary" | "json") picks either per call; see The content summary. (c) evaluate_affordability’s methodology.url is now its own page, /mortgage-affordability-calculator/methodology/ (was the mortgage P&I methodology). (d) The withholding-checkup prompt now names pre_tax_401k_annual, pre_tax_cafeteria_annual and pre_tax_deductions_annual instead of their deprecated camelCase spellings. On the hosted endpoint from 2026-09-27.

Compatibility: MINOR — every existing structured field keeps its name and value, and no figure moves; the output schemas only add source_links and provenance[].url. The behaviour that moves is content[0].text for requests that send MCP-Protocol-Version: those clients also receive structuredContent, which carries the full result; requests without the header see the pre-1.7.0 text.

1.6.0 · 2026-09-25 · Additive — versioned, diffable reference data

Every statutory dc:// resource now carries a version (the rule year plus the date its tables were last verified, e.g. 2026.20260924) and a content_hash (sha256: over the canonical JSON of the body without those two fields), so a client can cache a resource and tell for certain whether it changed. dc://irs/uniform-lifetime gains the published date the other two already carried. supersedes is now filled in from the years the server holds: dc://ssa/bend-points/2026 links the new dc://ssa/bend-points/2025. Two new resources: dc://ssa/bend-points/2025 and dc://ssa/bend-points/diff/2025..2026, a field-by-field rule-year diff (path, old value, new value). The same diff shape exists for dc://irs/limits/diff/{from}..{to} and appears for 2026..2027 when the 2027 IRS figures are added; no 2025 IRS resource is served, because the server does not hold a complete 2025 IRS record. On the hosted endpoint from 2026-09-27. See Versions, hashes and rule-year diffs.

Compatibility: MINOR — every existing resource body is its previous serialization plus the new fields; the one value that moves is supersedes on dc://ssa/bend-points/2026 (null → the 2025 URI). No tool, schema or figure changes.

1.5.0 · 2026-09-24 · Additive — ask the server for an outcome, and let the server ask you for a number

Two additive capabilities, each reached only by a call that opts into it. (a) Target mode on plan_retirement_income: an optional target: { metric, value, solve_for } input. State the outcome you want — a projected 401(k) balance at retirement (future_balance) or a Social Security monthly benefit (monthly_benefit) — and the tool solves for the input that reaches it by inverting its own forward projection with a bracketed goal-seek, rather than making you guess an input and re-call. “When can I retire?” is solve_for: "retirement_age". Solvable inputs are the dials you actually control: contribution_percent, annual_return_percent, retirement_age, balance and annual_salary for a balance target; claim_age and annual_salary for a benefit target. Inputs that are facts rather than dials (birth_year, years_worked, life_expectancy, the employer-match fields, the booleans) are refused by name with the reason. An unreachable target is answered, not refused: the result’s target block reports reached: false, the metric at both ends of the searched range, and modules_computed_at — the value the projection below it was actually computed at, which is not your target.

(b) Elicitation (Multi Round-Trip Requests): a call missing a required input can come back as resultType: "input_required" with an inputRequests map (one elicitation/create whose requestedSchema is derived from the tool’s own published input schema, so every field carries its real type, range and unit) plus an opaque requestState; collect the values and retry the original request with inputResponses. This is the protocol’s 2026-07-28 MRTR pattern, not the server-initiated elicitation that revision removed. Because this server keeps no session state, it cannot recall the capability you declared at initialize — so it asks only when the call declares support, via params._meta["info.digitalcalculator/elicitation"]: true. Without that key the behaviour is exactly 1.4.0’s. On the hosted endpoint from 2026-09-27.

Compatibility: MINOR — no previously-valid request changes shape, message or figure; the input schema adds target on plan_retirement_income only. Both new behaviours are opt-in, so a client written against 1.3.0 or 1.4.0 sees no change at all. The REST twins are untouched — MRTR is a JSON-RPC pattern and has no REST equivalent. See the API Reference entry.

1.4.0 · 2026-09-23 · Additive — a tenth tool: evaluate_affordability

A fifth verb-first scenario tool that answers “how much home can I afford?” from gross annual income, existing monthly debt, down payment, rate and term: it computes the front-end and back-end debt-to-income ratios at lender-standard targets (defaults 28/36, caller-adjustable) and searches for the maximum home price whose principal & interest keeps both ratios at or under target — the same amortization formula mortgage_monthly_payment uses, inverted by a bracketed goal-seek rather than re-derived. P&I only (an optional monthly_property_costs folds taxes, insurance, HOA and PMI in as a fixed monthly amount). Returns max_home_price, max_loan_amount, monthly_payment_at_max, both ratios, binding_constraint (which target capped the answer) and a note stating the scope, the targets applied and the search outcome. Listed after the four composites; REST twin at /v1/tools/evaluate-affordability/calculate; the methodology manifest gains its entry (tool_count 9 → 10); instructions now routes affordability questions to it instead of listing affordability as not offered. On the hosted endpoint from 2026-09-27.

Compatibility: MINOR — no existing request, figure or schema moves; tools/list gains one tool. Every 1.3.0-valid request remains 1.4.0-valid with identical figures. See the API Reference entry.

1.3.0 · 2026-09-23 · Additive — error classes, discoverable defaults, and a prompt that completes

INPUT_VALIDATION messages now name their failure class instead of one shared range message — missing ("<field> is required"), wrong type ("<field> must be a number/an integer/a string/a boolean"), and unknown argument ("unknown argument '<key>' — did you mean '<closest>'?" or "— no close match.", both naming the accepted keys); genuine out-of-range messages are unchanged. The 23 input properties whose description already stated a default (plan_retirement_income 7, evaluate_roth_conversion 2, check_contribution_eligibility 1, project_growth 2, paycheck_net_pay 5, emergency_fund_recommendation 6) now carry that default as a real JSON Schema default keyword. Tool descriptions no longer carry internal history (old identifiers, “absorbs the former …” clauses, file names). The instructions field was restructured from a 2,073-character unbroken paragraph into a line-broken, ≤1,500-character sequence (disclaimer, units, routing, provenance, resources). The retirement-readiness-review prompt now declares annual_return_percent (optional, stated fallback 7) so a host that collects exactly the prompt’s declared arguments can complete the review.

Compatibility: MINOR — the input schemas only gain default keywords; nothing is removed, retyped or revalued. Every 1.2.0-valid request remains 1.3.0-valid with identical figures. See the API Reference for the full wire and worked examples in the Quickstart.

1.2.0 · 2026-09-22 · Additive — protocol conformance (includes 1.1.0)

Tranche 1 (folded into this release rather than shipped separately as 1.1.0 in production): every JSON-RPC result carries resultType: "complete"; snake_case aliases replace camelCase as the advertised spelling for 17 arguments across the four single-quantity calculator tools (deprecated camelCase still works, marked in tools/list and flagged with a namespaced _meta marker); the anonymous 429 body became a JSON-RPC error object; capabilities.extensions["io.modelcontextprotocol/ui"] and _meta["openai/outputTemplate"] declared on view-bearing tools. Tranche 2: Bearer-tier 401/429 denials on /mcp became JSON-RPC error objects too (-32001 / -32000, distinct codes, HTTP status and rate-limit headers unchanged); the anonymous per-IP window now meters tools/call only — discovery methods (initialize, server/discover, ping, tools/list, resources/list, resources/read, prompts/list, prompts/get) are exempt; additionalProperties: false is now enforced (not just advertised) on tools/call for all ten tools; plan_retirement_income now returns non-empty provenance[]; ttlMs/cacheScope moved from a bare _meta key to top-level result fields on every list-shaped result, and to _meta["info.digitalcalculator/cache"] on resources/read.

Compatibility: MINOR on both tranches, with no figure moving. Two rules were tightened in a spec-compliant way rather than anything being removed: unknown top-level arguments, previously stripped silently, are now rejected with INPUT_VALIDATION (the schema always advertised additionalProperties: false, so a client written against the published contract was never sending them); and the Bearer denial body moved from a bare {"error":...} object into the JSON-RPC error envelope (HTTP status and every rate-limit/quota header unchanged). See the argument deprecation notice and the API Reference.

1.0.0 · 2026-08-07 · Breaking — contract 1.0.0: surface consolidation

The anonymous surface becomes 9 tools: four new verb-first scenario tools (plan_retirement_income, evaluate_roth_conversion, check_contribution_eligibility, project_growth) absorb eight granular tools; the four highest-traffic calculators and money_flow_map are kept. Adds the provenance envelope fields (rule_year, sources[]), three statutory reference-data resources (dc://irs/limits/2026, dc://irs/uniform-lifetime, dc://ssa/bend-points/2026), the prompts capability (3 prompts), a shared canonical vocabulary across every schema, and protocol revision 2026-07-28 support (server/discover, session-header-free operation, response cacheability advertisements). The -poc suffix retires. On the hosted endpoint from 2026-08-08.

Compatibility: the one deliberate breaking release of the early versions, made under the 0.x rules before any directory listing froze the surface. The scenario tools were checked to return the same figures as the tools they absorbed. REST compatibility: every pre-1.0 alias at api.digitalcalculator.info/v1/tools/{alias}/calculate keeps working indefinitely with its original request/response shapes — see the alias table.

v0.11.x · 2026-07-17 · Additive — money_flow_map joins the anonymous tier

money_flow_map now appears in the anonymous tools/list (14 tools) and the methodology manifest, callable without an API key under standard anonymous rate limits.

Compatibility: MINOR — a new tool appears on the anonymous surface; every existing tool’s response is unchanged.

v0.10.x · 2026-07-11 · Fix — results rounded to the cent, and truthful caveats added

Round-to-cents on all 13 calculator outputs plus caveat additions (RMD joint-life, 401(k) catch-up, HSA excess-contribution, IRA deductibility, and more).

Compatibility: new fields only; anonymous and authenticated answers stay identical; no breaking change.

v0.9.x · 2026-07-07 · Additive — money_flow_map (tool 15), for API keys at launch

Conversational budget → computed summary + interactive Sankey-map deep link, available with an API key (Bearer tier) at launch.

Compatibility: Bearer tier only — anonymous responses untouched; no breaking change.

v0.8.x · 2026-07-06 · Additive — generate_report (tool 14): PDF reports for API keys

Branded PDF report generation for Bearer-tier (API key) sessions.

Compatibility: Bearer tier only — anonymous responses untouched; no breaking change.

Policy · 2026-07-01 · Additive — the Versioning & Deprecation Contract is published

Published the formal MCP Tool Versioning & Deprecation Contract, with notice windows of 90 days for anonymous callers and 180 days for API-key (Bearer) customers.

Compatibility: no change to any request or response.

Server update · 2026-06 · Additive — API keys (Bearer tier)

Bearer-tier authentication foundation: calls can carry an API key in the Authorization header.

Compatibility: a call without an Authorization header is answered exactly as before; no breaking change.

v0.4.3 · 2026-06-12 · Additive — the stdio adapter forwards to the hosted endpoint

stdio↔HTTPS transport-adapter architecture; MCP Registry submission metadata; 13 tools at that release.

Compatibility: anonymous answers unchanged; no breaking change.

v0.3.0 · 2026-05-27 · Additive — the retirement cluster

Retirement cluster added (IRA, Roth conversion, RMD, HSA) → 9 tools.

Compatibility: existing tools unchanged; no breaking change.

v0.2.1 · 2026-05-27 · Fix — packaging and licence files

Packaging polish: the MIT LICENSE and the hosted-API terms (LICENSE-API.md) ship as standalone files in the npm package.

Compatibility: no change to any request or response.

v0.2.0 · 2026-05-22 · Breaking — hosted Streamable HTTP endpoint; two tools renamed

Hosted Streamable-HTTP cutover. Two tools were renamed, so a caller integrated against v0.1.0 had to update those tool names. Engine versions were reset to 1.0.0; the math did not change.

Compatibility: the figures each tool returns are unchanged; the two renamed tools need their new names.

v0.1.0 · 2026-05-09 · Additive — first public release

First public shim release. 5 tools.

Compatibility: initial release.

See Also