io.bildata/bildata
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Danish vehicle registration tax (registreringsafgift) calculator and DMR registration statistics
| Author | io.bildata |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 3249 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"bildata": {
"url": "https://bildata.io/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (6)
calculate_registreringsafgiftCalculate DANISH vehicle registration tax (registreringsafgift) for a new or used personbil, varebil or motorcykel under registreringsafgiftsloven. Same engine and validation as bildata.io's public calculator. Amounts in DKK; an estimate, not an official Motorstyrelsen valuation. REQUIRED PAIRS: condition="new" needs bruttovaerdi; condition="used" needs handelspris AND nypris (nypris is the used vehicle's own original price when new, not the new-vehicle price field). ALWAYS send co2 for a petrol, diesel or hybrid PERSONBIL or VAREBIL: an omitted co2 counts as 0 g/km, i.e. battery-electric, and makes the tax far too low with no error raised — zero on an ordinary car, and still only a fraction of the real figure on an expensive one. On motorcykel co2 does not select the drivetrain at all - isElectric does. Send every number as a JSON number (300000, not "300000"), use enum values exactly as listed, and OMIT an optional field you do not know rather than sending null.
Parameters:
vehicleType(required) — string — Vehicle category under Danish lawcondition(required) — string — new = first registration of a new vehicle; used = import/revaluation of a used vehicleco2— number — WLTP CO2 in g/km. PERSONBIL and VAREBIL: send it for any fuel-burning vehicle - an omitted value and an explicit 0 are BOTH read as battery-electric (EV phase-in and EV bundfradrag), which makes the tax far too low. Use 0 only for a pure EV. MOTORCYKEL: co2 does not select the drivetrain here; isElectric does, and a motorcykel sent with co2=0 and no isElectric is priced as fuel-burning.aaben— boolean — Varebil only: open cargo bed (ladvogn)avgKm— number — Used: average odometer km of the comparable adverts. Part of the actualKm/avgKm/vehicleAgeYears set — a partial send is silently ignored.nypris— number — Used vehicles: REQUIRED when condition="used". The SAME vehicle's original price as new in DKK, incl. all taxes. Unused when condition="new" — for a new vehicle use bruttovaerdi.actualKm— number — Used: actual odometer km. The km regulation is skipped entirely unless actualKm, avgKm, vehicleAgeYears AND handelspris are all present.elForbrug— number — Electric consumption in Wh/km. Send WITH elRaekkevidde — the battery deduction is (elForbrug/1000) * elRaekkevidde, so either one alone is a no-op.isElectric— boolean — MOTORCYKEL: the EV switch for that vehicle type. For personbil and varebil the drivetrain comes from co2 (0 or absent = electric), so this flag does not change the tax — but DO send it for a battery-electric personbil or varebil: it is read as your declaration that the missing co2 is deliberate, and suppresses the warning that the answer looks too low.targetYear— number — Rules year to calculate under (default: current). A year with no published table silently falls back to the current rates; the answer's rules_year says which table actually applied.totalvaegt— number — Varebil only: total weight in kghandelspris— number — Used vehicles: REQUIRED when condition="used". Current Danish trade price in DKK, incl. registration tax. Unused when condition="new".bruttovaerdi— number — New vehicles: REQUIRED when condition="new" (unused when condition="used"). Taxable value in DKK, i.e. price incl. VAT and margin BEFORE registration tax. NOT the advertised Danish showroom price, which already contains the tax being calculated.elRaekkevidde— number — Electric range in km (WLTP). Send WITH elForbrug — either one alone is a no-op.condition_stand— string — Used: maintenance condition (vedligeholdelsesstand)vehicleAgeYears— number — Used: vehicle age in years since first registration. Also used on its own for the under-6-months rule, so send it even when you cannot supply the km set. The km regulation additionally needs actualKm, avgKm and handelspris — that part is skipped unless all are present.allDealerListings— boolean — Used: true only if EVERY comparable advert is a dealer listing (enables annoncefradrag + leveringsomkostninger)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_afgift_ratesMachine-readable Danish vehicle registration tax rates 2026–2029: skalaknæk (brackets), CO2 tiers, bundfradrag and EV/plug-in phase-in (indfasning) percentages per year. Identical to GET https://bildata.io/api/afgift-prognose/rates. 2027–2029 rates are provisional.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
forecast_registreringsafgiftProject DANISH registration tax for a NEW vehicle across rules-years 2026–2029 (the EV/plug-in phase-in schedule changes the tax each year). Returns per-year results and deltas vs 2026. Amounts in DKK. Estimates, not official valuations. NEW vehicles only, and always the whole 2026-2029 span: for a USED import, or for a single year, use calculate_registreringsafgift instead. Send every number as a JSON number (300000, not "300000").
Parameters:
vehicleType(required) — string — Vehicle category under Danish lawnypris(required) — number — Price as new in DKK (taxable value)co2— number — WLTP CO2 in g/km. PERSONBIL and VAREBIL: send it for any fuel-burning vehicle - an omitted value and an explicit 0 are BOTH read as battery-electric (EV phase-in and EV bundfradrag), which makes the tax far too low. Use 0 only for a pure EV. MOTORCYKEL behaves differently on THIS tool: an explicit co2=0 counts as electric, but an OMITTED co2 does NOT - the bike is priced as fuel-burning and the tax comes out far too HIGH. Declare an electric motorcykel with isElectric=true.aaben— boolean — Varebil only: open cargo bed (ladvogn)isElectric— boolean — MOTORCYKEL: the EV switch for that vehicle type, and on this tool the only reliable way to declare one - leave it unset with co2 omitted and the bike is priced as fuel-burning. For personbil and varebil the drivetrain comes from co2 (0 or absent = electric), so this flag does not change the tax.totalvaegt— number — Varebil only: total weight in kgelectricRange— number — Electric range kmbatteryCapacity— number — Battery kWh (used with electricRange to derive Wh/km)electricConsumption— number — Electric consumption Wh/km (overrides battery/range derivation)
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_market_statsDanish new-vehicle registration statistics from bildata.io (weekly DMR data). Dimensions: fuel_type, brands (top 20), evs, imports (vehicles brought in from abroad, by toldsyn date: counts, share, top makes), monthly_totals (last 12 months incl. leasing series), country_of_origin. kind=all covers every vehicle type; kind=Personbil passenger cars only. as_of is the data cutoff of the underlying extract — a month whose as_of is before month-end is PARTIAL. Market-level ONLY: the brands dimension is the top 20 brands and there is no per-model breakdown here — for a named MODEL use get_model_stats. It is NOT a way to get a brand total for a brand outside the top 20: a brand-only query there returns that brand's individual model rows (default 5, max 10, truncation disclosed in `note`) and defaults to kind=Personbil where this tool defaults to kind=all, so summing them does not reproduce a brand total from here.
Parameters:
dimension(required) — string — Which slice to return; exactly one per callkind— string — Default: all
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_model_statsLook up Danish registration numbers for a SPECIFIC car model by name — e.g. "Tesla Model Y", "VW ID.4", "Skoda Enyaq". Covers every model since 2018. Use this when the question names a model or brand; get_top_models only covers the top sellers of one month, and get_market_stats only the top 20 brands. A model still selling returns period figures (this month, this year, last year, market share) plus all-time totals. A model with no registration in the last ~3 years returns ONLY lifetime totals and its first/last registration date — the period figures do not exist for it and are listed in `unavailableFields`; their absence is missing data, NOT zero sales. Spelling is forgiving (ID.4 = ID 4 = id4, Citroen = Citroën) and the response states which row it matched and how, so verify `name` before quoting the numbers.
Parameters:
query(required) — string — Model or brand name, e.g. "Tesla Model Y" or "Toyota"kind— string — Default: Personbil (passenger cars)limit— integer — Max matches to return, default 5grouped— boolean — Default true: trims collapsed into canonical models (Enyaq 85 -> Skoda Enyaq), matching bildata.io/stats. false returns raw registry variants.
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
get_top_modelsTop-selling car models (and variants) in Denmark for a given month, from bildata.io's top-50 statistics (passenger cars, monthly, 12-month rolling window). Default: latest month, top 10. as_of is the data cutoff — if it is before month-end, the month is PARTIAL, not complete. A RANKING, bounded by the 12-month window. A model outside that month's top 50 is absent here — look that one up by name with get_model_stats. A month OLDER than the window cannot be answered by any tool on this server: get_model_stats reports fixed periods relative to today (this month, this year, last year, all-time), never an arbitrary past month.
Parameters:
limit— integer — Rows per list, default 10, max 50month— string — YYYY-MM; default latest available
Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.