# io.bildata/bildata

> Danish vehicle registration tax (registreringsafgift) calculator and DMR registration statistics

- name: io.bildata/bildata
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.bildata%2Fbildata
- tools: https://api.protogrid.dev/v1/servers/io.bildata%2Fbildata/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "bildata": {
      "type": "http",
      "url": "https://bildata.io/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% ~updated-53d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: calculate_registreringsafgift (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); forecast_registreringsafgift (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_model_stats (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,753 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 1 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 2,753 tokens to load them all
- tool set hash: d28e95695430561ae9f1164fdc30e4a2
- tools last changed: 2026-10-06T14:11:40.736Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.bildata/bildata.svg)](https://protogrid.dev/servers/io.bildata/bildata)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-06 `get_market_stats` changed (description)
  - before: Danish new-vehicle registration statistics from bildata.io (weekly DMR data). Dimensions: fuel_type, brands (top 20), evs, imports (top imported 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.
  - after: Danish 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.

Full history: https://api.protogrid.dev/v1/servers/io.bildata%2Fbildata/changes

## Remotes

- https://bildata.io/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `calculate_registreringsafgift`: Calculate 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.
- `forecast_registreringsafgift`: Project 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").
- `get_afgift_rates`: Machine-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.
- `get_market_stats`: Danish 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.
- `get_model_stats`: Look 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.
- `get_top_models`: Top-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.