# Spain Open Data > Market sizing, prices, rents, crime and locations in Spain from INE and other public data - name: io.github.digvijaysingh-ai/spain-open-data-mcp - version: 0.1.4 - connection class: R0 (autonomous) - trust: 97/100 - quality: 94/100 (new) - owner: not claimed - descriptor: https://api.protogrid.dev/v1/servers/io.github.digvijaysingh-ai%2Fspain-open-data-mcp - tools: https://api.protogrid.dev/v1/servers/io.github.digvijaysingh-ai%2Fspain-open-data-mcp/tools **An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe. ## Connection (mcpServers) ```json { "mcpServers": { "spain-open-data-mcp": { "type": "http", "url": "https://spain-open-data-mcp-165703905656.europe-west1.run.app/mcp" } } } ``` ## Trust - hygiene: 100 - liveness: 100 - freshness: 100 - provenance: 90 - drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-3d-ago - Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. ## Quality 94/100 (new) ### protocol: 88 (weight 25) - pass `protocol.modern`: supports 2026-07-28 (server/discover) - pass `protocol.stateless`: answers without a session - pass `protocol.transport`: streamable HTTP - warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use ### 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: 100 (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 - pass `tools.annotations`: 13 of 13 tools declare readOnlyHint or destructiveHint - pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint - pass `tools.token_cost`: about 4,453 tokens to load every tool - pass `tools.api_dump`: tools are not a one-to-one API dump ### stability: n/a (weight 15) - n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 3 of the 7 days needed ### dependencies: n/a (weight 15) - n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know spain-open-data-mcp@0.1.4 - tools: 13, about 4,453 tokens to load them all - tool set hash: 7021b83047b96ee907320c189d934aba - tools last changed: 2026-10-17T20:45:46.140Z - badge: [![protogrid quality](https://protogrid.dev/badge/io.github.digvijaysingh-ai/spain-open-data-mcp.svg)](https://protogrid.dev/servers/io.github.digvijaysingh-ai/spain-open-data-mcp) - Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. ### Tool changes - 2026-10-17 `crime` changed (outputSchema) - 2026-10-17 `rents` changed (outputSchema) - 2026-10-17 `price_band` changed (outputSchema) - 2026-10-17 `compare_areas` changed (outputSchema) - 2026-10-17 `income` changed (outputSchema) - 2026-10-17 `demographics` changed (outputSchema) - 2026-10-17 `resolve_place` changed (description, outputSchema) - before: Find the INE code and level (CCAA, province, municipality, district, tract) for a place in Spain. Use this first when a question names a place. Returns the best match first, with alternatives (e.g. 'Valencia' is both a city and a province). Handles accents, Basque, Catalan and Galician names, and common English names (Seville, Catalonia). Neighbourhood names are not supported; use districts or tracts from `demographics` or `income` with `sub_areas`. - after: Find the INE code and level (CCAA, province, municipality, district, tract) for a place in Spain. Use this first when a question names a place. Returns the best match first, with alternatives (e.g. 'Valencia' is both a city and a province). Handles accents, Basque, Catalan and Galician names, and common English names (Seville, Catalonia). Districts and tracts are shown with the OpenStreetMap neighbourhood names inside them ('Valladolid distrito 10 (Parquesol, Girón, La Victoria)'), and a neighbourhood name ('Parquesol, Valladolid', 'Gràcia, Barcelona') returns the INE district that contains it. - 2026-10-17 `compare_areas` changed (description) - before: Rank areas by opportunity for a business category: where is there most market per business. Each area gets a yearly market in euros, estimated competing businesses and an opportunity score against its region, all with ranges. Areas are ranked by the cautious (low) end of the score; areas too small for the category are left out and counted. Use for "where in Valladolid should I open a gym" or "which towns in Málaga province lack pharmacies". - after: Rank areas by market per competing business for a category (the opportunity score). Each area gets a yearly market in euros, estimated competing businesses and an opportunity score against its region, all with ranges. Areas are ranked by the cautious (low) end of the score; areas too small for the category are left out and counted. Use for "where in Valladolid should I open a gym" or "which towns in Málaga province lack pharmacies". - 2026-10-17 `market_size` changed (description) - before: Size the yearly market for a business category in a place in Spain, in euros, with a range. Market = households × INE household spending on the category × an income adjustment. Supply = competing businesses, calibrated against INE's company directory. Returns market per business and an opportunity score against the region (1.0 = same as the region), with every assumption listed. Assumptions can be overridden to test scenarios. Use for "how big is the market for X in Y" and "is Y under-served for X". - after: Size the yearly market for a business category in a place in Spain, in euros, with a range. Market = households × INE household spending on the category × an income adjustment. Supply = competing businesses, calibrated against INE's company directory. Returns market per business and an opportunity score: market per business against the region (1.0 = same as the region), not a forecast of openings. Every assumption is listed. Assumptions can be overridden to test scenarios. Use for "how big is the market for X in Y" and "is Y under-served for X". Full history: https://api.protogrid.dev/v1/servers/io.github.digvijaysingh-ai%2Fspain-open-data-mcp/changes ## Dependencies - pypi spain-open-data-mcp@0.1.4: unknown Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. ## Remotes - https://spain-open-data-mcp-165703905656.europe-west1.run.app/mcp (streamable-http, auth none, reachable true, uptime30d 1) ## Packages - pypi spain-open-data-mcp@0.1.4 ## Tools (13) - `businesses`: Count businesses of a kind in a place in Spain, per 10,000 residents and per km², from OpenStreetMap. Use it to size competition and supply: how many gyms, cafés or dentists an area has, how that compares with the province, region and Spain, which brands dominate, and which districts or tracts are over- or under-served (rank sub-areas by per_10k_residents). Counts are lower bounds because OpenStreetMap is mapped by volunteers; where INE's company directory covers the same activity, the result says how complete the map looks in that region. Returns counts and brands only, never lists of individual premises. - `catchment`: Profile the area within a radius (or a walking time) of an address: residents, households, income, age, and the businesses mapped there. With a category, also the yearly market in euros, competing businesses and an opportunity score against the region. Use for "who lives within 800 m of this shop" or "is there room for a bakery near Calle X". Addresses are checked against the municipality they name; ambiguous ones are refused with suggestions. - `chart`: Draw a chart (PNG) of a tool result: an opportunity ranking with ranges, income by district, an age pyramid or a population trend. Returns the image, the same text and sources as the underlying tool, and a source line on the image. If drawing fails the text still comes back. - `compare_areas`: Rank areas by market per competing business for a category (the opportunity score). Each area gets a yearly market in euros, estimated competing businesses and an opportunity score against its region, all with ranges. Areas are ranked by the cautious (low) end of the score; areas too small for the category are left out and counted. Use for "where in Valladolid should I open a gym" or "which towns in Málaga province lack pharmacies". - `crime`: Recorded crime in a place from the Interior ministry: offences by type (theft, burglary, robbery, assault, drugs, cybercrime and more) for the latest full year, per 1,000 residents, the change on the year before, the latest year-to-date figures, and province, region and Spain for comparison. Published for municipalities over 20,000 residents, provinces and regions; smaller places get the province's figures, and the result says so. - `demographics`: Population, sex, five-year age bands, 5-year trend, and household profile for a place in Spain. Municipality, province and CCAA: census population by age band (latest 1 January), cross-checked against the official Padrón figure. District and tract: census age bands and sex from INE's file by census tract. Municipality, district and tract: household size, single-person households, mean age, share under 18 and 65+ from INE's income atlas. Use sub_areas to compare a city's districts or tracts, e.g. to find where young families or older residents concentrate. - `find_datasets`: Search Spain's national open-data catalogue (datos.gob.es) for datasets on a topic. Returns each dataset's title, publisher, licence, file formats, update frequency and last change, and an id to pass to read_dataset. Use when a question needs data this server does not hold directly (parking, licences, local events, tourist offices, transport). - `income`: Household income for a place in Spain from INE's income atlas, down to census tract. Returns net and gross income per person and per household, mean and median per consumption unit, inequality (Gini, P80/P20), income sources (wages, pensions, benefits), a trend, and benchmarks against the province, region and Spain. Use it for purchasing power, price positioning and choosing between districts. Figures are euros of the data year; the atlas runs about two years behind. - `market_size`: Size the yearly market for a business category in a place in Spain, in euros, with a range. Market = households × INE household spending on the category × an income adjustment. Supply = competing businesses, calibrated against INE's company directory. Returns market per business and an opportunity score: market per business against the region (1.0 = same as the region), not a forecast of openings. Every assumption is listed. Assumptions can be overridden to test scenarios. Use for "how big is the market for X in Y" and "is Y under-served for X". - `price_band`: Suggest a price range for a place from local purchasing power and inflation. Public data has no competitor prices, so this adjusts a price you know (from elsewhere or an earlier date) to this place today: CPI for the category's group since that month, then local median income per consumption unit against the reference place. Returns a range from no local adjustment to full adjustment, labelled as an estimate. - `read_dataset`: Read a datos.gob.es dataset: its columns and up to 20 sample rows, with its licence. Reads CSV and JSON files listed in the catalogue (the first 5 MB). Columns that look like personal data (names, ID numbers, emails, phones) are withheld. Values are shown as the publisher published them. - `rents`: How housing rents have changed in a place: INE's rent index (IPVA, 2015 = 100) with the change over the last year, five years and since 2015, against province, region and Spain. Covers municipalities over 10,000 residents, districts of provincial capitals, provinces and regions (not the Basque Country or Navarra). Gives changes, not rents in euros. - `resolve_place`: Find the INE code and level (CCAA, province, municipality, district, tract) for a place in Spain. Use this first when a question names a place. Returns the best match first, with alternatives (e.g. 'Valencia' is both a city and a province). Handles accents, Basque, Catalan and Galician names, and common English names (Seville, Catalonia). Districts and tracts are shown with the OpenStreetMap neighbourhood names inside them ('Valladolid distrito 10 (Parquesol, Girón, La Victoria)'), and a neighbourhood name ('Parquesol, Valladolid', 'Gràcia, Barcelona') returns the INE district that contains it.