Belgium Data Desk
REMOTE · DATA.VECTURE.BE
Belgian official open data: dataset search, Statbel figures, air, rivers, weather and trains.
Available components
Last scanned (17 hours ago)
Scores higher than 46% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Data and Analytics
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability59
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 8127 tokens (~406/item across 20 items; 20 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management20
- Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 20 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (12)
- TLS certificate
- Authorization
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 +1
- “belgian_statistics” reworded the description of “places” cosmetic
1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.
- 19 Nov 26 0
- Tool “preview_dataset” rewrote its description, which is the text the model reads security
- 18 Nov 26 +1
- Schema quality: 7187 → 8104 ▼ functional
- New tool “heritage_at_location” functional
- New tool “zoning_at_location” functional
- “search_datasets” added an optional parameter “covers_year” cosmetic
- “search_datasets” added an optional parameter “language” cosmetic
- 17 Nov 26 0
- New tool “electricity_grid” functional
- 16 Nov 26 +1
- Tool “river_levels” rewrote its description, which is the text the model reads security
- Tool “train_punctuality” rewrote its description, which is the text the model reads security
- Tool “weather” rewrote its description, which is the text the model reads security
- Stability: unverified → 0.03 ▲ functional
- “train_punctuality” added an optional parameter “from_station” cosmetic
- “train_punctuality” added an optional parameter “to_station” cosmetic
- Tool “river_levels” changed its title: River, canal and tide levels in Flanders now (waterinfo.be) → River, canal and tide levels in Flanders now and forecast (waterinfo.be) cosmetic
- Tool “train_punctuality” changed its title: Belgian train punctuality: station, train, IC line, national (Infrabel) → Belgian train punctuality: journey, station, train, IC line, national (Infrabel) cosmetic
- 15 Nov 26 62
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://data.vecture.be/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=vecture.be | CN=WE1,O=Google Trust Services,C=US | 8 Nov 2026 | 6 Feb 2027 | ECDSA 256 | ECDSA-SHA256 | 75c032584501f13d0ecd443c6252f11e |
| SANs: vecture.be, data.vecture.be, *.data.vecture.be | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of data.vecture.be. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| be. | DS published | 45588 | 13 | Verified |
| vecture.be. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://data.vecture.be/mcp | Verified | 200 | |
| http (plaintext) | http://data.vecture.be/mcp | Inconclusive | 405 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
air_quality Air quality at a place in Belgium (now, forecast, annual) ~416
Air quality at an address or point anywhere in Belgium from IRCEL-CELINE, read live: this hour's modelled NO2, PM2.5, PM10, ozone and black carbon for the 4 km cell, the last 24-hour PM means against the WHO 24-hour guidelines, the BelAQI forecast for today and the next three days (1 excellent to 10 horrible), annual means of the last complete year (street level in Flanders via ATMO-Street, 4 km background elsewhere) compared with the WHO 2021 guidelines and the current and 2030 EU limit values, and the nearest measuring stations that are reporting now (out-of-service stations are skipped and named). Includes the municipality (NIS code) with its population and income. Starts with key_facts; cite IRCEL-CELINE (CC BY 4.0). Examples: How is the air in central Brussels now, and over the year? → {"address":"Rue Neuve 1, 1000 Bruxelles"}; Air quality forecast for Liège → {"address":"Place Saint-Lambert 1, 4000 Liège"}; Annual NO2 at street level near Antwerp central station → {"latitude":51.2194,"longitude":4.4025}.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Address in Belgium, e.g. 'Grote Markt 1, 3000 Leuven' or 'Place Saint-Lambert 1, 4000 Liège'. |
| latitude | number | – | WGS84 latitude, e.g. 51.0453 (use with longitude instead of address). |
| longitude | number | – | WGS84 longitude, e.g. 3.7275. |
| x_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) x in metres, as an alternative to latitude/longitude. |
| y_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) y in metres. |
No output schema declared.
No examples provided.
belgian_statistics Official Belgian statistics: population, income, prices, labour market ~552
Answers with Statbel's official figures (not dataset links). Places: any of the 565 municipalities (2025 boundaries; Dutch, French or pre-merger names such as Melle work; NIS codes too), the provinces, the three regions or Belgium. topic 'profile' (default) gives population on 1 January (total, sex, age bands, non-Belgian nationality, change since 2019) and average net taxable income per inhabitant and per declaration (income years up to the latest published); a single municipality comes with its province, region and Belgium for comparison. rank_by ranks municipalities within a province, region or Belgium (e.g. highest income per inhabitant in Limburg, oldest population); with no places, topic 'population' or 'income' ranks the municipalities of Belgium by it. topic 'prices' gives the latest CPI, inflation and (smoothed) health index read live from Statbel; topic 'labour' gives the latest quarterly employment, unemployment and activity rates for Belgium and the regions (Labour Force Survey). Each answer starts with key_facts and states reference dates, definitions and the Statbel citation (CC BY 4.0). Examples: How many people live in Ghent? → {"places":["Gent"],"topic":"population"}; The largest municipalities in Belgium (no places: ranks by population) → {"topic":"population"}; Which municipalities in Limburg have the highest income per inhabitant? → {"rank_by":"income_per_inhabitant","within":"Limburg","limit":5}; What is the current inflation and health index? → {"topic":"prices"}.
| Name | Type | Req | Description |
|---|---|---|---|
| income_year | integer | – | Income year, default the latest published. |
| limit | integer | – | With rank_by; default 10. |
| order | string | – | With rank_by; default highest. |
| places | array | – | Up to 6 places for population/income, e.g. ['Leuven','Gent'] or ['44088']. For topic 'labour', only Belgium and the three regions are available, not municipalities or provinces. A bare 'Brussels' mea… |
| rank_by | string | – | Rank municipalities by this indicator instead of listing places. |
| topic | string | – | Default 'profile' (population and income). |
| with_context | boolean | – | Default true: one municipality is shown with its province, region and Belgium. |
| within | string | – | With rank_by: a province, region or 'Belgium' (default). |
| year | integer | – | Population year (1 January), 2019 to the latest; default latest. |
No output schema declared.
No examples provided.
catalogue_overview Catalogue overview ~42
Counts of the catalogue by scope and topic, the date it was built, and when file links were last checked: what is available and how fresh the evidence is.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
contact_publisher Draft a message to a dataset's publisher ~379
Prepare a message to the people who publish a dataset, for the user to send themselves: the contact the publisher declared in its catalogue record (never a guessed address), a polite draft in the publisher's language (Dutch, French, English or German) naming the dataset, file, issue and the evidence checked, and a mailto: link. Nothing is sent by this tool. Use it when the user wants to report a problem (stale data, broken link, missing units or metadata, wrong values) or ask the publisher a question. Run get_dataset or preview_dataset first and pass what they showed as evidence; the answer says what to check before writing. Show the draft to the user to edit and send; send one message per problem, not one per related dataset. Example: {"id":"national:d04b704a-1672-4567-bf0d-9a9452618812","issue":"metadata","details":"The record says 2019 but the file has 2026 data."}.
| Name | Type | Req | Description |
|---|---|---|---|
| details | string | – | What is wrong or what the user wants to know, in the user's words (at most 1,500 characters). |
| evidence | array | – | Up to 5 facts checked with the other tools, each with its source, e.g. 'preview_dataset: TIMESTAMP_EXTRACT goes up to 2026-11-01, catalogue says 2019-01-21'. |
| id | string | yes | Dataset id from search_datasets or get_dataset. |
| issue | string | yes | What the message is about: stale, access, metadata, units, values, missing, schema, licence or question. |
| language | string | – | Language of the draft; default the publisher's (Dutch for Flemish bodies, French for Walloon and Brussels ones, else English). |
No output schema declared.
No examples provided.
electricity_grid Belgian electricity: consumption, solar, wind, imports, prices now and forecast (Elia) ~374
Belgium's electricity system from Elia's open data (the transmission system operator). Without a date: the latest quarter-hour of consumption (total load), solar and wind production and their share, net imports or exports per border, today's and tomorrow's peak load and solar and wind energy, the latest imbalance price with today's range and negative-price quarter-hours, and yesterday's generation mix by fuel (nuclear, gas, wind, solar...) with its CO2 intensity. With a past date (from 2015; solar from October 2020, mix from 2020, imbalance prices from 22 May 2024, CO2 from October 2024): that day's consumption, peak, solar, wind, border flows, imbalance prices, mix and CO2. With a future date (up to 10 days): Elia's forecast of load (7 days), solar (10) and wind (6). Days are Brussels days; values are quarter-hour averages in MW, energies in GWh. Solar and wind are Elia's estimates for all installations, rooftop panels included. Does not give the day-ahead market price (EPEX SPOT), household tariffs, outages at an address or gas-network data. Examples: How much of Belgium's electricity comes from solar and wind right now, and is Belgium importing? → {}; How much solar and wind power is expected in Belgium tomorrow? → {"date":"tomorrow"}; How much solar power did Belgium produce on 21 June 2026, and were there negative prices? → {"date":"2026-06-21"}.
| Name | Type | Req | Description |
|---|---|---|---|
| date | string | – | A Brussels day as YYYY-MM-DD, e.g. '2026-11-15', or 'today', 'tomorrow', 'yesterday'. Default today (the situation now). |
No output schema declared.
No examples provided.
fetch Fetch (deep-research compatible) ~30
Fetch the full catalogue record for an id returned by search.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Record id from search. |
No output schema declared.
No examples provided.
flood_risk Flood-prone classes at a place in Flanders (official VMM maps) ~320
Whether an address or point in Flanders is flood-prone on the official VMM maps of flood-prone areas from rivers (fluvial), heavy rain (pluvial) and the sea, each as class A (no flooding modelled), B (small chance under climate change), C (small chance) or D (medium chance). These maps underlie the flood information required when property in Flanders is sold or let and the water test for permits. Includes the municipality (NIS code) with its population and income. Flanders only. Starts with key_facts; describes the location, not a building's floor level or defences. Examples: Is the Grote Markt in Leuven flood-prone? → {"address":"Grote Markt 1, 3000 Leuven"}; Flood classes at a point in Ghent → {"latitude":51.05,"longitude":3.72}.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Address in Flanders, e.g. 'Groenplaats 1, 2000 Antwerpen'. |
| latitude | number | – | WGS84 latitude, e.g. 51.0453 (use with longitude instead of address). |
| longitude | number | – | WGS84 longitude, e.g. 3.7275. |
| x_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) x in metres, as an alternative to latitude/longitude. |
| y_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) y in metres. |
No output schema declared.
No examples provided.
get_dataset Get one dataset record ~216
Full catalogue record for one dataset id from search_datasets: publisher, licence and what it allows, update cycle, contact, description, file links, publisher-declared columns, link-check evidence, and whether preview_dataset can read the file. For files checked weekly it adds a dataset card computed from the file itself: whether it is overdue against its declared update cycle, the period the data covers, join keys (NIS municipality codes incl. pre-2025 codes, enterprise numbers, postcodes, coordinates), sparse and constant columns, column changes since the last check, and quotable facts each with its evidence. Fields the publisher leaves empty are listed under not_declared_by_publisher with the source page; for analysis over the whole file, the analysis block gives download links and the domains a sandbox must allow. Example: {"id":"national:d04b704a-1672-4567-bf0d-9a9452618812"}.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Dataset id as returned by search_datasets. |
No output schema declared.
No examples provided.
get_subsurface_record Borehole, CPT or groundwater-well details from DOV ~371
Details of one DOV record by id from subsurface_at_location: for a borehole ('boring/…') its depth, purpose and layer-by-layer interpretations (formal stratigraphy with formation names, the logged lithological description, hydrogeological units) plus ids of further interpretations; for a groundwater screen ('filter/…') the aquifer, screen depth, water levels (latest, lowest, highest, last 12 readings, yearly means) and groundwater quality (every result of the latest lab sample, and trends of nitrate, chloride, sulphate, ammonium, conductivity and pH); for a CPT ('sondering/…') cone resistance and sleeve friction per metre with the Robertson soil behaviour type; for a soil profile ('bodemlocatie/…') its classification, site (water table, drainage, land use, parent material) and per horizon the Munsell colour, texture, organic carbon, pH and lime; or one interpretation ('interpretatie/…'). Codes are decoded with DOV's published code lists; every answer starts with key_facts. Examples: Layer-by-layer log of one borehole → {"id":"boring/2016-140688"}; Water levels and groundwater quality at one monitoring screen → {"id":"filter/1978-006372"}; Soil behaviour per metre from one cone penetration test → {"id":"sondering/1984-065526"}.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Record id such as 'boring/2016-140688', 'filter/1978-006372', 'sondering/1984-065526', 'bodemlocatie/1964-007478' or 'interpretatie/1993-088861' (a DOV URL for the record also works). |
No output schema declared.
No examples provided.
heritage_at_location Heritage designations at a place in Flanders (Onroerend Erfgoed) ~419
Whether an address or point in Flanders is protected or listed heritage, and what that means for works and permits, from the Flemish heritage agency (Onroerend Erfgoed) via the public Mercator map service. Checks every legal designation at the point: protected monument, protected town or village view, protected landscape, protected archaeological site, transition zone, UNESCO core or buffer zone, fixed inventory of built or landscape heritage, fixed archaeological zone (archaeology note needed for smaller works), heritage landscape and area where no archaeology is expected (no archaeology note needed). Each comes with its name, id, date, the official decision link and what it means. Also the scientific inventory of built heritage (no legal effect), ratified archaeology notes at the point, protected monuments within 30 m, and the municipality (NIS code). Flanders only. Starts with key_facts. Checks one point, not a whole parcel; does not replace the permit procedure or give zoning (spatial plans). Examples: Is the building on Bruges' Markt protected heritage? → {"address":"Markt 1, 8000 Brugge"}; Is Leuven station a protected monument? → {"address":"Martelarenplein 20, 3000 Leuven"}; Which heritage rules apply at this point in Antwerp? → {"latitude":51.2194,"longitude":4.4025}.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Address in Flanders, e.g. 'Markt 1, 8000 Brugge'. |
| latitude | number | – | WGS84 latitude, e.g. 51.0453 (use with longitude instead of address). |
| longitude | number | – | WGS84 longitude, e.g. 3.7275. |
| x_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) x in metres, as an alternative to latitude/longitude. |
| y_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) y in metres. |
No output schema declared.
No examples provided.
preview_dataset Preview the rows of a dataset file ~199
Read the first rows of a dataset's CSV/TSV file directly from the publisher and return the column names, inferred column types, the delimiter and encoding, and up to 20 sample rows as published. Works for datasets whose get_dataset record shows preview_available: true. Normally reads the first 64 KiB (up to 256 KiB only when the first CSV record is very wide), so it shows structure and example values, not totals over the whole file; for those, its analysis block gives the download links, a DuckDB query in the file's own dialect and the domains to allow in a sandbox. Example: {"id":"national:d04b704a-1672-4567-bf0d-9a9452618812","rows":5}.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Dataset id as returned by search_datasets or get_dataset. |
| rows | integer | – | Number of sample rows, default 10. |
No output schema declared.
No examples provided.
real_estate_prices House and apartment sale prices in Belgium (Statbel) ~488
What homes sell for in any of the 565 municipalities (2025 boundaries; Dutch, French or pre-merger names and NIS codes work), a province, a region or Belgium, from Statbel's official real-estate sales statistics (deeds of sale, 2010 to the latest full year plus the latest half-year). For houses (all, or terraced/semi-detached with 2-3 facades, or detached with 4+ facades) and apartments: the median price, the 25th and 75th percentile, the number of sales and the change of the median over five years. rank_by 'median_price' ranks municipalities within a province, region or Belgium, leaving out places with too few sales for a comparable median. Starts with key_facts; says when a figure rests on few sales. Prices are nominal sale prices of the homes that happened to be sold, not valuations of a specific home, and not rents. Examples: What does a house or an apartment cost in Mechelen compared with Leuven? → {"places":["Mechelen","Leuven"]}; Where in Limburg are houses most expensive? → {"rank_by":"median_price","within":"Limburg","type":"house","limit":5}; Median apartment price in Belgium in 2020 → {"places":["Belgium"],"type":"apartment","year":2020}.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | With rank_by; default 10. |
| min_sales | integer | – | With rank_by: leave out municipalities with fewer sales than this, default 20. |
| order | string | – | With rank_by; default highest. |
| places | array | – | Up to 6 places to compare, e.g. ['Mechelen','Leuven'], ['Limburg','Flanders','Belgium'] or ['44088']. Default Belgium. |
| rank_by | string | – | Rank municipalities by median price of one type (default houses) instead of listing places. |
| type | string | – | Default 'all' (houses and apartments). h23 = terraced or semi-detached houses, h4 = detached houses. |
| within | string | – | With rank_by: a province, region or 'Belgium' (default). |
| year | integer | – | Sale year, 2010 to the latest full year; default the latest. |
No output schema declared.
No examples provided.
river_levels River, canal and tide levels in Flanders now and forecast (waterinfo.be) ~697
Live water levels at about 650 river, canal and tidal gauges in Flanders and on the Flemish waterways (VMM and HIC, waterinfo.be): the nearest gauges to an address or point, a named gauge, or the gauges on a river. For each gauge: the level now in metres TAW (and above the gauge zero where that is how it is published), the change over 1, 3 and 24 hours (rising/falling/steady, or low and high water for tidal gauges), the 24-hour minimum and maximum, how far it is below the gauge's official watch and alarm levels, whether it is within its usual range (the long-term band of 80 % of the time), the publisher's official alarm status and its short-term forecast status, and, at about 360 gauges, the publisher's own water-level forecast for the next 48-60 hours (peak level and time, rise, when the watch or alarm level would be reached, forecast rain over the catchment; for tidal gauges the next high and low waters). Starts with key_facts. Values are provisional measurements updated every 5-15 minutes. Does not say whether a specific address will flood (use flood_risk for Flanders' official flood-prone maps), and does not cover Wallonia (SPW's terms forbid passing its gauge data on), Brussels' Flowbru gauges or discharge. Forecasts are deterministic model runs, not certainties. Examples: How high is the Dijle at Korbeek-Dijle, and how far from the alarm level? → {"station":"Korbeek-Dijle"}; Is the Demer rising near Diest? → {"address":"Grote Markt 1, 3290 Diest","river":"Demer"}; Water levels around Ghent now → {"address":"Korenmarkt 1, 9000 Gent","radius_km":5}; When is high tide in the Scheldt at Antwerp? → {"latitude":51.2213,"longitude":4.3977,"max_stations":2}.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Address or place, e.g. 'Grote Markt 1, 3000 Leuven': the nearest gauges are returned. |
| latitude | number | – | WGS84 latitude, e.g. 51.0453 (use with longitude instead of address). |
| longitude | number | – | WGS84 longitude, e.g. 3.7275. |
| max_stations | integer | – | How many gauges to return, default 3. |
| radius_km | number | – | Search radius around the place in km, default 10. |
| river | string | – | Only gauges on this river or canal, e.g. 'Demer', 'Zeeschelde', 'Dender', 'Kanaal Gent-Terneuzen'; combine with an address to get that stretch. |
| station | string | – | A gauge by name or number instead of a place, e.g. 'Korbeek-Dijle', 'L08_097', 'Werchter', 'Antwerpen tij'. |
| x_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) x in metres, as an alternative to latitude/longitude. |
| y_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) y in metres. |
No output schema declared.
No examples provided.
search Search (deep-research compatible) ~42
Search Belgian open-data records. Returns result ids, titles and landing-page URLs; use fetch with an id for the full record.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | Search query. |
No output schema declared.
No examples provided.
search_datasets Search Belgian open datasets ~383
Search Belgian open data (about 21,700 records from federal, regional and local publishers: hand-reviewed national registers, data.gov.be and directly harvested portals) in Dutch, French or English. For common needs such as population, the enterprise register (KBO/BCE), air quality, unemployment or train punctuality, the official reference source is listed first, marked authoritative_source, with a guidance block saying who publishes it and the usual pitfalls. Scope 'datasets' (default) means data files and APIs; map layers, PDF publications, research supplements and metadata-only records are separate scopes. Results are catalogue metadata and link-check evidence, not statements about data correctness. Examples: {"query":"bevolking per gemeente"}; {"query":"thuisbatterij"}; {"query":"census 2021","open_licence_only":true}; {"query":"wegenregister","scope":"maps"}; {"query":"luchtkwaliteit","topic":"environment","limit":5}.
| Name | Type | Req | Description |
|---|---|---|---|
| covers_year | integer | – | Only records whose data covers this year (the period the publisher declares, or the dates read from the file). Records with no known period are left out. |
| language | string | – | Only records whose publisher declares this language. Records with no declared language are left out. |
| limit | integer | – | Number of results, default 10. |
| open_licence_only | boolean | – | Only records whose licence permits reuse (open or share-alike). |
| query | string | yes | Words in Dutch, French or English, e.g. 'population by municipality' or 'bevolking gemeente'. |
| scope | string | – | Kind of record. Default 'datasets'. |
| topic | string | – | Optional topic id: geology, water, energy, transport, health, population, economy, environment, agriculture, education, government, places, other. |
No output schema declared.
No examples provided.
search_subsurface Find boreholes, wells, CPTs, soil profiles or groundwater permits in Flanders ~719
Find DOV records by area and attributes, e.g. the deepest boreholes in a municipality, geothermal boreholes since 2020, groundwater wells in the Brussel sand with quality data, electric CPTs near an address, soil profiles with lab data, or the largest groundwater abstraction permits in a municipality (with the licensed total per aquifer). Area: a municipality (official 2025 boundary; old pre-merger names work), or an address/coordinates with radius_m, or nothing for all of Flanders. Filtering and sorting run on DOV's server, so counts cover every matching record. Use get_subsurface_record with a result id for details. Examples: The deepest boreholes in Leuven → {"record_type":"boreholes","municipality":"Leuven","limit":3}; Geothermal boreholes drilled in Flanders since 2020 → {"record_type":"boreholes","purpose":"geothermal","date_from":"2020","limit":5}; The largest groundwater abstraction permits in Ghent → {"record_type":"groundwater_permits","municipality":"Gent","sort":"largest","limit":5}.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Address in Flanders, as an alternative to municipality (then radius_m applies). |
| aquifer | string | – | Wells and permits: HCOV code (A0620, or A06 for the whole system) or words from the unit name ('Brussel', 'Krijt'). |
| cpt_method | string | – | CPTs: electric CPTs also measure sleeve friction. |
| date_from | string | – | YYYY, YYYY-MM or YYYY-MM-DD: drilling/test date, last water-level date for wells, permit start, survey date. |
| date_to | string | – | Same formats as date_from. |
| latitude | number | – | WGS84 latitude, e.g. 51.0453 (use with longitude instead of address). |
| limit | integer | – | Results to list, default 10. |
| longitude | number | – | WGS84 longitude, e.g. 3.7275. |
| max_depth_m | number | – | Maximum depth, same fields. |
| min_annual_m3 | number | – | Permits: minimum licensed annual volume in m³. |
| min_depth_m | number | – | Minimum depth (borehole or CPT depth, well screen bottom, permitted well depth). |
| municipality | string | – | Municipality in Flanders, e.g. 'Leuven' or 'Merelbeke-Melle'. |
| purpose | string | – | Boreholes: why it was drilled. |
| radius_m | integer | – | Radius around the address or coordinates, default 1000 m. |
| record_type | string | yes | What to find. |
| sort | string | – | Default: nearest with a location; otherwise deepest (boreholes, CPTs), newest (wells), largest (permits), most_described (soil profiles). |
| with_lab_data | boolean | – | Soil profiles: only those with lab samples. |
| with_quality_data | boolean | – | Wells: only screens with groundwater quality samples. |
| with_stratigraphy | boolean | – | Boreholes: only those with a formal, hydrogeological or Quaternary stratigraphy. |
| x_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) x in metres, as an alternative to latitude/longitude. |
| y_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) y in metres. |
No output schema declared.
No examples provided.
subsurface_at_location Soil, geology and groundwater at a place in Flanders ~528
What is under a location in Flanders, read live from Databank Ondergrond Vlaanderen (DOV), the Flemish Government's subsurface database: the soil-map unit, the Tertiary and Quaternary geological map units and the groundwater bodies at the point, whether it lies in a drinking-water protection zone, the modelled column of geological and hydrogeological (aquifer) units with depths from DOV's 3D models (an answer even where no borehole exists), the boreholes, cone penetration tests (CPT) and groundwater monitoring wells within radius_m (counts plus the nearest and deepest, with ids), groundwater abstraction permits and described soil profiles within at least 1 km (licensed volume per aquifer; names of private persons withheld), and the current shallow groundwater status at the nearest status well. Starts with key_facts: the answer in a few sentences. Give an address in Flanders, or latitude/longitude, or Lambert 72 x/y. Use get_subsurface_record with a returned id for layer-by-layer borehole logs, CPT profiles or groundwater levels and quality. Map units and the model column are map- and model-scale information, not a site investigation. Examples: What is under the Grote Markt in Leuven? → {"address":"Grote Markt 1, 3000 Leuven"}; Deep aquifers and boreholes near Antwerp central station, for a geothermal question → {"latitude":51.2194,"longitude":4.4025,"radius_m":500,"max_depth_m":1000}.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Address in Flanders, e.g. 'Grote Markt 1, 3000 Leuven'. Looked up in the Flemish address register. |
| latitude | number | – | WGS84 latitude, e.g. 51.0453 (use with longitude instead of address). |
| longitude | number | – | WGS84 longitude, e.g. 3.7275. |
| max_depth_m | integer | – | Deepest unit start listed in the modelled column, default 300 m; deeper units are counted. Raise it for deep geothermal or deep aquifer questions. |
| radius_m | integer | – | Search radius for boreholes, CPTs and wells in metres, default 250. |
| x_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) x in metres, as an alternative to latitude/longitude. |
| y_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) y in metres. |
No output schema declared.
No examples provided.
train_punctuality Belgian train punctuality: journey, station, train, IC line, national (Infrabel) ~717
How punctual Belgian trains are, from Infrabel's official open data. Between two stations (from_station and to_station, e.g. a commute): every direct train that stopped at both yesterday, how many arrived less than 6 minutes late, average and worst delays, scheduled against actual journey time, morning and evening peak, the return direction, and the two stations' monthly figures. For a station (name in Dutch, French or English, or the nearest one to an address): the share of trains arriving less than 6 minutes late in the latest month against the average over all stops, its rank, the last 13 months, yesterday train by train (delay bands, average delay, the latest trains) and major incidents there. For a train number: every point it passed yesterday with its delays, where the delay grew and whether it was on time at the official measuring points. For an IC line (e.g. 'IC 01'): monthly punctuality per direction and by time of day against the national figure. With none of these: the national figure (also counting cancellations), by train type, punctuality lost by cause, cancellations per operator, the month's major incidents (delay minutes, cancelled trains), and today so far. Starts with key_facts. Does not give live departures or platform changes, and has no train-by-train data before yesterday. Examples: How punctual is the commute from Leuven to Brussels-Central? → {"from_station":"Leuven","to_station":"Brussel-Centraal"}; How punctual are trains at Leuven station? → {"station":"Leuven"}; Was train 2112 late yesterday, and where did it lose time? → {"train_number":"2112"}; How punctual is the IC 01 Oostende-Eupen? → {"ic_line":"IC 01"}.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | An address or place instead of a station: the nearest station is used, e.g. 'Grote Markt 1, 2800 Mechelen'. |
| from_station | string | – | With to_station: trains between two stations yesterday, e.g. 'Leuven'. |
| ic_line | string | – | An InterCity line, e.g. 'IC 01', 'IC 16-1' or 'IC3'. |
| latitude | number | – | WGS84 latitude, e.g. 51.0453 (use with longitude instead of address). |
| longitude | number | – | WGS84 longitude, e.g. 3.7275. |
| month | string | – | Month for the monthly figures as YYYY-MM, e.g. '2026-03'; default the latest Infrabel published. |
| station | string | – | A passenger station, e.g. 'Leuven', 'Bruxelles-Midi', 'Gent-Sint-Pieters', 'Luik-Guillemins'. |
| to_station | string | – | With from_station: where the trains arrive, e.g. 'Brussel-Centraal', 'Bruxelles-Central'. |
| train_number | string | – | A train number as on the departure board, e.g. '2112': its run yesterday stop by stop. |
| x_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) x in metres, as an alternative to latitude/longitude. |
| y_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) y in metres. |
No output schema declared.
No examples provided.
weather Weather now, last days and 48-hour forecast in Belgium (KMI/IRM) ~504
The weather at an address or point in Belgium from the Royal Meteorological Institute (KMI/IRM) open data: what the nearest synoptic station measures now (temperature, wind and gusts, humidity, cloud cover, pressure), its last 24 hours (minimum, maximum, precipitation), the last 7 days at the nearest automatic station (daily rain, max/min, sunshine), and KMI's ALARO model forecast for that point for the next 48 hours (3-hourly for the first day: temperature, precipitation, snow, wind, gusts, cloud cover) with 24-hour summaries and when rain is first expected, plus KMI's official weather warnings (yellow, orange, red for wind, rain, snow and ice, thunderstorms, fog, heat, cold, the coast) in force or announced for that place's province and, at the coast, the coastal zone, read live from KMI's feed on EUMETNET MeteoAlarm with the original warning text. Starts with key_facts (a warning comes first). Observations come from a station up to tens of km away; the forecast is a single deterministic model run without probabilities. Does not give climate normals, rain radar or forecasts beyond about 60 hours. Examples: What is the weather in Leuven now, and will it rain tomorrow? → {"address":"Grote Markt 1, 3000 Leuven"}; Weather forecast for Liège for the next two days → {"address":"Place Saint-Lambert 1, 4000 Liège"}; How windy is it at the coast in Ostend, and is there a storm warning? → {"latitude":51.2194,"longitude":2.9269}.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Address or place in Belgium, e.g. 'Grote Markt 1, 3000 Leuven' or 'Place Saint-Lambert 1, 4000 Liège'. |
| latitude | number | – | WGS84 latitude, e.g. 51.0453 (use with longitude instead of address). |
| longitude | number | – | WGS84 longitude, e.g. 3.7275. |
| x_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) x in metres, as an alternative to latitude/longitude. |
| y_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) y in metres. |
No output schema declared.
No examples provided.
zoning_at_location Zoning and spatial plans at a place in Flanders (Departement Omgeving) ~437
What the spatial plans say about an address or point in Flanders, from the Department of Environment's official planning data (Digitaal Stedenbouwkundige Informatie) via Mercator. Names the land-use zone that applies: the most detailed plan in force (municipal, provincial or regional spatial implementation plan, special or general plan of development, or the regional zoning plan), with its code, category, publication date and a link to its rules, and lists the plans underneath. Also overlays, building-line and expropriation plans, municipal and provincial urban-development regulations, plans and regulations still in procedure (with participation dates), and permit applications filed through the Omgevingsloket since 2017 (type, works, status, link; applicants not named). Includes the municipality (NIS code). Flanders only. Starts with key_facts. Checks one point; it is not the official planning certificate (stedenbouwkundig uittreksel) and does not interpret the plan rules for a project. For heritage designations use heritage_at_location. Examples: What may be built at this address in Leuven? → {"address":"Tiensesteenweg 150, 3001 Leuven"}; Which plan applies at Leuven station? → {"address":"Martelarenplein 20, 3000 Leuven"}; What is the zoning at this point in Ghent? → {"latitude":51.0543,"longitude":3.7174}.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | – | Address in Flanders, e.g. 'Tiensesteenweg 150, 3001 Leuven'. |
| latitude | number | – | WGS84 latitude, e.g. 51.0453 (use with longitude instead of address). |
| longitude | number | – | WGS84 longitude, e.g. 3.7275. |
| x_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) x in metres, as an alternative to latitude/longitude. |
| y_lambert72 | number | – | Belgian Lambert 72 (EPSG:31370) y in metres. |
No output schema declared.
No examples provided.
How do I install the Belgium Data Desk MCP server?
Belgium Data Desk is a hosted endpoint at https://data.vecture.be/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · data.vecture.be
claude mcp add --transport http vecture-be-belgium-data-desk 'https://data.vecture.be/mcp'
What is the Belgium Data Desk MCP server?
Belgium Data Desk is an MCP server listed in the public MCP registry as io.github.vecture-be/belgium-data-desk. Belgian official open data: dataset search, Statbel figures, air, rivers, weather and trains. This page covers its hosted endpoint (https://data.vecture.be/mcp).
Is the Belgium Data Desk MCP server safe to use?
Belgium Data Desk scores 65 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Belgium Data Desk MCP server expose?
Belgium Data Desk exposes 20 tools: search_datasets, get_dataset, preview_dataset, catalogue_overview, contact_publisher, and 15 more. Their descriptions and schemas cost roughly 7,833 tokens of context every time the server is loaded.
Does the Belgium Data Desk MCP server require authentication?
No. We connected to Belgium Data Desk without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Belgium Data Desk MCP server still maintained?
Belgium Data Desk is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Belgium Data Desk MCP server?
VerifyMCP ran 12 checks on Belgium Data Desk, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Belgium Data Desk: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.