# Portugal (public data) (pypi · portugal-mcp)

Portugal public data: IPMA weather, INE, Banco de Portugal, Parliament, contracts, SNS, fuel.

- Trust score: 61/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `portugal-mcp`: 61/100 (this document), [markdown](https://verifymcp.io/servers/thiagojacoblannes-portugal-mcp/portugal-mcp.md), [page](https://verifymcp.io/servers/thiagojacoblannes-portugal-mcp/portugal-mcp)

## Channel facts

- Registry: `pypi`
- Package: `portugal-mcp`
- Version: `0.2.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 49/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 3 of 34 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to ThiagoJacobLannes/portugal-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 2 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 8957 tokens (~190/item across 47 items; 47 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 47 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 48 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Portugal (public data) MCP server?

Portugal (public data) runs locally as a PyPI package, launched with uvx portugal-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add thiagojacoblannes-portugal-mcp -- uvx portugal-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "thiagojacoblannes-portugal-mcp": {
      "command": "uvx",
      "args": [
        "portugal-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "thiagojacoblannes-portugal-mcp": {
      "command": "uvx",
      "args": [
        "portugal-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add thiagojacoblannes-portugal-mcp -- uvx portugal-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "thiagojacoblannes-portugal-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "portugal-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add thiagojacoblannes-portugal-mcp --command uvx --arg portugal-mcp
```

### Hermes

```yaml
mcp_servers:
  thiagojacoblannes-portugal-mcp:
    command: "uvx"
    args: ["portugal-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "thiagojacoblannes-portugal-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "portugal-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add thiagojacoblannes-portugal-mcp -t stdio -c uvx -a portugal-mcp
```

### Other

```json
{
  "mcpServers": {
    "thiagojacoblannes-portugal-mcp": {
      "command": "uvx",
      "args": [
        "portugal-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 61, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-03 (score 76, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-02 (score 61)

First indexed and scored.

## MCP tools (47)

### `weather_forecast` (~118 tokens)

5-day weather forecast for a place in Portugal (IPMA, official).

Args:
    place: district capital or island town, e.g. "Lisboa", "Porto", "Faro", "Funchal", "Ponta Delgada".
    lat, lon: use instead of place for anywhere else; the nearest IPMA forecast location is used.
Returns daily min/max temperature, rain probability, weather type, wind, and today's UV index.

Input parameters:

- `lat`
- `lon`
- `place`

### `weather_warnings` (~94 tokens)

Active IPMA weather warnings (rain, wind, heat, cold, snow, fog, sea, thunderstorms).

Args:
    area: optional district or island group, e.g. "Lisboa", "Madeira", "Açores". Omit for the whole country.
    include_green: also list green (no-warning) entries. Default false.

Input parameters:

- `area`
- `include_green` (boolean)

### `fire_risk` (~103 tokens)

Wildfire danger (RCM, risco de incêndio rural) for a municipality, today or tomorrow.

Args:
    municipality: concelho name, e.g. "Sintra", "Monchique".
    day: 0 = today, 1 = tomorrow.
Scale: 1 reduzido, 2 moderado, 3 elevado, 4 muito elevado, 5 máximo.

Input parameters:

- `day` (integer)
- `municipality` (string, required)

### `sea_forecast` (~108 tokens)

Coastal sea forecast: wave height and period, wave direction, sea temperature (IPMA).

Args:
    place: coastal spot, e.g. "Nazaré", "Peniche", "Faro", "Funchal". Or pass lat/lon for the nearest one.
    day: 0 = today, 1 = tomorrow, 2 = the day after.

Input parameters:

- `day` (integer)
- `lat`
- `lon`
- `place`

### `earthquakes` (~102 tokens)

Recent earthquakes recorded by IPMA.

Args:
    region: "mainland" (mainland Portugal and Madeira) or "azores".
    days: look back this many days (max 30).
    min_magnitude: only quakes at or above this magnitude.
    limit: max rows (newest first).

Input parameters:

- `days` (integer)
- `limit` (integer)
- `min_magnitude` (number)
- `region` (string)

### `postal_code` (~54 tokens)

Look up a Portuguese postal code (código postal, 'XXXX-XXX' or 'XXXX').

Returns district, municipality, locality and the streets the code covers, plus a central point.

Input parameters:

- `code` (string, required)

### `where_is` (~42 tokens)

Which parish, municipality and district a coordinate is in, plus altitude, land use and hazard maps.

Input parameters:

- `lat` (number, required)
- `lon` (number, required)

### `municipality` (~42 tokens)

A municipality (concelho): district, INE code, area, parishes, 2021 census, town-hall contacts.

Input parameters:

- `name` (string, required)

### `public_holidays` (~86 tokens)

Portugal's national public holidays for a year (default: this year), with weekday.

Carnival is listed as optional: it is usually a day off by government decision, not by law.
Municipal holidays (one per concelho, e.g. Lisbon 13 June, Porto 24 June) are not included.

Input parameters:

- `upcoming_only` (boolean)
- `year`

### `ine_search` (~120 tokens)

Find INE indicators by keyword (e.g. "inflação", "desemprego", "população", "rendas", "turismo").

Searches INE's catalogue of key indicators. Returns varcd codes to pass to ine_indicator.
Any other INE indicator can be read with ine_indicator if you know its code (from www.ine.pt).
Args:
    lang: "PT" (more complete wording) or "EN".

Input parameters:

- `lang` (string)
- `limit` (integer)
- `query` (string, required)

### `ine_indicator` (~177 tokens)

Values of an INE indicator, latest periods first.

Args:
    varcd: 7-digit indicator code from ine_search, e.g. "0008074".
    place: geography name to keep, e.g. "Portugal", "Lisboa", "Norte", "Porto". Default: "Portugal"
        when present, otherwise all geographies.
    periods: how many of the latest reference periods to return (1-24).
    category: keep only rows whose category labels contain this text (e.g. "Total", "Mulheres").
    lang: "PT" or "EN".
    limit: max rows.

Input parameters:

- `category`
- `lang` (string)
- `limit` (integer)
- `periods` (integer)
- `place`
- `varcd` (string, required)

### `bpstat_search` (~171 tokens)

Find Banco de Portugal statistical series by keyword.

Examples: "euribor 12 meses", "taxa de juro novos empréstimos habitação", "dólar", "dívida pública",
"depósitos particulares", "preços habitação". The search picks the most likely statistical domains
(or the one you pass as domain_id) and searches the series inside them; it also lists every domain
so you can retry with a specific domain_id. The first search of a domain takes a few seconds to a
minute; then it is cached for a week.
Args:
    lang: "PT" or "EN" (labels are richer in PT).

Input parameters:

- `domain_id`
- `lang` (string)
- `limit` (integer)
- `query` (string, required)

### `bpstat_series` (~123 tokens)

Observations of Banco de Portugal series (ids from bpstat_search).

Args:
    series_ids: one or more series ids (max 10), e.g. [12559924].
    last_n: latest observations per series (1-500). Ignored when `since` is given.
    since: "YYYY-MM-DD" — return every observation from this date.
    lang: "PT" or "EN".

Input parameters:

- `lang` (string)
- `last_n` (integer)
- `series_ids` (array, required)
- `since`

### `parliament_search` (~219 tokens)

Search initiatives in the Portuguese Parliament: bills, resolutions, inquiries.

Args:
    query: words in the title, e.g. "habitação", "IRS", "imigração".
    type: e.g. "Projeto de Lei", "Proposta de Lei" (Government bills), "Projeto de Resolução".
    author: party acronym ("PS", "PSD", "CH", "IL", "L", "PCP", "BE", "CDS-PP", "PAN", "JPP") or "Governo".
    result: "aprovado" or "rejeitado" — keeps initiatives whose latest vote had this result.
    since: "YYYY-MM-DD" — submitted on or after this date.
    legislature: Roman numeral, default the current one (XVII).
    limit: max results, newest first.

Input parameters:

- `author`
- `legislature`
- `limit` (integer)
- `query`
- `result`
- `since`
- `type`

### `parliament_initiative` (~77 tokens)

Full record of one initiative: every phase with dates, every vote with each group's position, text link.

Args:
    initiative_id: the `id` from parliament_search (e.g. "356403"), or a reference like "Proposta de Lei 3".

Input parameters:

- `initiative_id` (string, required)
- `legislature`

### `parliament_votes` (~121 tokens)

Recent plenary votes, with how each parliamentary group voted.

Args:
    party: show this group's position on each vote (e.g. "PS", "CH"); only votes where it is recorded.
    query: words in the initiative title.
    since: "YYYY-MM-DD".
    result: "aprovado" or "rejeitado".
    limit: max votes, newest first.

Input parameters:

- `legislature`
- `limit` (integer)
- `party`
- `query`
- `result`
- `since`

### `parliament_deputies` (~139 tokens)

Members of Parliament (deputados): party, constituency (círculo), status. Seats per party included.

Args:
    name: part of the parliamentary or full name.
    party: group acronym, e.g. "PSD", "PS", "CH".
    constituency: e.g. "Lisboa", "Porto", "Açores", "Europa".
    include_inactive: also list deputies who left or were replaced. Default false.

Input parameters:

- `constituency`
- `include_inactive` (boolean)
- `legislature`
- `limit` (integer)
- `name`
- `party`

### `public_contracts` (~211 tokens)

Search Portuguese public contracts (Portal BASE) for one year.

Args:
    query: words in the contract object, e.g. "software", "limpeza", "ambulâncias".
    buyer: public body name or 9-digit NIF, e.g. "Município de Lisboa", "SPMS".
    supplier: company name or NIF.
    procedure: e.g. "Ajuste Direto", "Concurso público", "Consulta Prévia".
    min_value, max_value: contract price range in euros.
    year: contract-file year (default: this year; 2012 onwards).
    sort: "value" (largest first) or "date" (newest first).
    limit: max rows.

Input parameters:

- `buyer`
- `limit` (integer)
- `max_value`
- `min_value`
- `procedure`
- `query`
- `sort` (string)
- `supplier`
- `year`

### `public_contracts_summary` (~111 tokens)

Totals for one buyer or supplier in a year: number of contracts, total value, by procedure, top partners.

Args:
    entity: name or 9-digit NIF of a public body or a company.
    role: "buyer", "supplier" or "any".
    year: default this year.
    top: how many top counterparties to list.

Input parameters:

- `entity` (string, required)
- `role` (string)
- `top` (integer)
- `year`

### `open_data_search` (~107 tokens)

Search the datasets of Portugal's national open-data portal (dados.gov.pt).

Args:
    query: e.g. "acidentes rodoviários", "escolas", "qualidade do ar", "alojamento local".
    organization: optional publisher name to filter by, e.g. "INE", "Câmara Municipal de Lisboa".
    limit: max results (1-50).

Input parameters:

- `limit` (integer)
- `organization`
- `query` (string, required)

### `open_data_dataset` (~35 tokens)

Details and downloadable files of one dados.gov.pt dataset (id or slug from open_data_search).

Input parameters:

- `dataset` (string, required)

### `open_data_preview` (~77 tokens)

First rows of a CSV or JSON file hosted on dados.gov.pt (reads at most 512 KB).

Args:
    url: a resource url from open_data_dataset (must be on dados.gov.pt).
    rows: how many rows to return (1-100).

Input parameters:

- `rows` (integer)
- `url` (string, required)

### `sns_find_institutions` (~331 tokens)

Find SNS hospitals / local health units (ULS) by name, or the nearest ones to a coordinate.

Use this first when the user names a hospital or a place ("hospitals near Lisbon",
"is there an emergency department near 38.72,-9.14?"), then pass `stats_entity` to
sns_emergency_stats / sns_surgery_wait_stats / sns_consultation_wait_stats.

Each result: name, its parent ULS, coordinates, distance_km (when lat/lon given), whether
it reports emergency / consultation / surgery data on tempos.min-saude.pt, and
\`stats_entity` — the name under which the official statistics report it (statistics are
per ULS / hospital group, not per building). This list does NOT contain live waiting times;
for live emergency waits send the user to https://tempos.min-saude.pt.

Args:
    query:          Part of the name, accent-insensitive, e.g. "Santa Maria", "Faro", "ULS Algarve".
    lat, lon:       Sort by distance from this point (WGS84), e.g. Lisbon 38.7223, -9.1393.
                    Without `query`, umbrella ULS entries are skipped (they duplicate a hospital's location).
    emergency_only: Only places that report emergency-department data.
    limit:          Max results (default 10, max 50).

Input parameters:

- `emergency_only` (boolean)
- `lat`
- `limit` (integer)
- `lon`
- `query`

### `sns_emergency_stats` (~367 tokens)

Emergency-department (urgência) visits per month: by type and by Manchester triage colour.

Use for "how busy is the ER at X?", "how many emergency visits in the Algarve last month?",
"what share of ER visits are green/blue (non-urgent)?". OFFICIAL MONTHLY STATISTICS ONLY —
not the live queue (the latest month is usually 2-3 months back and provisional). For live
waiting times send the user to https://tempos.min-saude.pt. Not medical advice: in an
emergency call 112; SNS 24 (808 24 24 24) for advice.

Scope: one institution, one region, or (neither) all of mainland Portugal's SNS hospitals.

Per period (latest first): visits_in_month and visits_year_to_date by type (general,
paediatric, obstetric, psychiatric, total), triage_in_month by colour (red = immediate,
orange = very urgent, yellow = urgent, green = less urgent, blue = non-urgent, white = not
clinical / other) and triage_share_in_month_pct.

Args:
    institution: Hospital or ULS name, accent-insensitive ("Santa Maria", "São João",
                 "Hospital de Faro"). A hospital is mapped to its ULS; check `scope`.
    region:      Norte | Centro | LVT (Lisboa) | Alentejo | Algarve. Ignored if institution is given.
    period:      Latest month to include, "YYYY-MM" (default: newest available).
    months:      How many months back to return (default 6, max 24).

Input parameters:

- `institution`
- `months` (integer)
- `period`
- `region`

### `sns_surgery_wait_stats` (~352 tokens)

Surgery access indicators per month: surgical waiting list, % within the guaranteed
maximum time, mean days from admission to surgery, and surgeries performed.

Use for "how long is the wait for surgery at X?", "how many people are on the surgery list
in the Norte region?", "how many operations did hospital Y do?". Official monthly statistics
(latest month usually 2-3 months back, provisional). The open data has NO breakdown by
specialty or procedure — say so if asked for one.

Per period (latest first):
  \- waiting_list: patients on the surgical waiting list (LIC) at month end, how many are
    still within the legal maximum guaranteed response time (TMRG, 180 days for normal
    priority since 2018) and the % within it.
  \- mean_days_before_surgery_in_month / _year_to_date: average days between hospital
    admission and the operation for scheduled inpatient surgery (this is NOT the time on
    the waiting list).
  \- surgeries_in_month / surgeries_year_to_date: scheduled (= inpatient + day surgery) and urgent.

Args:
    institution: Hospital or ULS name ("Santa Maria", "Coimbra", "IPO Porto"); mapped to its ULS.
    region:      Norte | Centro | LVT (Lisboa) | Alentejo | Algarve. Ignored if institution is given.
    period:      Latest month to include, "YYYY-MM" (default: newest available).
    months:      How many months back (default 6, max 24).

Input parameters:

- `institution`
- `months` (integer)
- `period`
- `region`

### `sns_consultation_wait_stats` (~259 tokens)

Hospital outpatient consultations per month and the % of FIRST specialist consultations
(referred by a family doctor via CTH/SIGA) held within the guaranteed maximum time (TMRG).

Use for "how long is the wait for a first hospital appointment at X?", "is hospital Y on
time with first consultations?", "how many consultations did the Centro region do?".
Official monthly statistics (latest month usually 2-3 months back, provisional); there is no
breakdown by specialty in the open data.

Per period (latest first): consultations_in_month / _year_to_date (total, first,
subsequent) and first_consultations_within_max_time_pct for the month and year-to-date.

Args:
    institution: Hospital or ULS name; mapped to its ULS.
    region:      Norte | Centro | LVT (Lisboa) | Alentejo | Algarve. Ignored if institution is given.
    period:      Latest month to include, "YYYY-MM" (default: newest available).
    months:      How many months back (default 6, max 24).

Input parameters:

- `institution`
- `months` (integer)
- `period`
- `region`

### `sns_search_datasets` (~197 tokens)

Search the ~150 datasets of the SNS Transparency portal (titles and descriptions are in Portuguese).

Use when the curated tools don't cover the question — e.g. hospital bed occupancy
("ocupação"), births/caesareans ("partos"), INEM pre-hospital calls, SNS 24 calls, family
doctor coverage ("médico de família", "inscritos"), medicines spending, staff ("trabalhadores"),
cancer screening ("rastreios"). Then call sns_query_dataset with the dataset_id and the field names
returned here. Portuguese keywords work best; matching is accent-insensitive.

Args:
    query: Keywords, e.g. "ocupação internamento", "partos", "urgência". Empty = list all (id + title).
    limit: Max results (default 10, max 50; ignored when listing all).

Input parameters:

- `limit` (integer)
- `query`

### `sns_query_dataset` (~346 tokens)

Run an ODSQL query on any SNS Transparency portal dataset (Opendatasoft Explore API v2.1).

Use after sns_search_datasets for anything the curated tools don't cover. Clauses are ODSQL:
  \- where:    `instituicao like "santa maria" and tempo >= date'2026-01-01'`
              (`like` is a case- and accent-insensitive "contains"; dates use date'YYYY-MM-DD')
  \- select:   `tempo, instituicao, total_urgencias` or aggregates `sum(total_urgencias) as total`
  \- group_by: `regiao` or `tempo`  (combine with aggregates in select)
  \- order_by: `tempo desc`
Most hospital-activity datasets (field `tempo`, monthly) store YEAR-TO-DATE CUMULATIVE
values: December is the annual total; a single month = this month minus the previous one.
Many datasets have a `regiao` and an `instituicao` (or `entidade`) field. Official statistics,
not live data.

Args:
    dataset_id: e.g. "ocupacao-do-internamento" (from sns_search_datasets).
    where, select, group_by, order_by: ODSQL clauses (optional).
    limit:  Rows to return (default 20, max 100).
    offset: Skip rows, for paging.

Input parameters:

- `dataset_id` (string, required)
- `group_by`
- `limit` (integer)
- `offset` (integer)
- `order_by`
- `select`
- `where`

### `medicine_availability` (~278 tokens)

Is a medicine in shortage in Portugal? Checks Infarmed's published availability information.

Use when someone can't find a medicine, or asks whether X is in shortage ("rutura",
"esgotado", "falta"). Searches by brand or active substance (Portuguese names work best,
e.g. "quetiapina", "Ozempic", "ácido acetilsalicílico"; dose and form narrow it,
e.g. "quetiapina 300 mg libertação prolongada").

Checks, all from www.infarmed.pt (latest versions are found automatically):
  \- shortages Infarmed is actively monitoring (with its circulars and advice);
  \- the monthly list of medicines whose export is temporarily suspended because of
    shortage / supply risk in Portugal;
  \- the quarterly prior-notification list (LNP) of medicines with availability concerns.

status is one or more of: monitored_shortage, export_suspended, prior_notification,
no_issue_in_published_lists. "No issue" does not prove the medicine is available:
Infarmed's full shortage search is not queried (see not_checked).

Args:
    medicine: Brand name or active substance, optionally with strength/form.
    limit:    Max rows returned per list (default 15).

Input parameters:

- `limit` (integer)
- `medicine` (string, required)

### `pharmacies` (~334 tokens)

Pharmacies in a Portuguese municipality, with which ones are on duty today and open now.

Use for "farmácia de serviço em X", "pharmacy open now near me", or to list pharmacies
to call. Each pharmacy has name, address, phone, coordinates, today's hours, open_now,
on_duty (official duty roster for the duty day 09:00-09:00) and the duty type
(e.g. "Permanente - Aberta 24h"). Results are sorted: on duty first, then open now,
then distance (when lat/lon are given). Stock is not public: never say a pharmacy has a
medicine.

Args:
    city:          Municipality or town/parish, e.g. "Lisboa", "Porto", "Cascais",
                   "Alvalade, Lisboa" (add ", <municipality>" to disambiguate a town).
    lat, lon:      Optional user position: adds distance_km and allows radius_km. With
                   no city, the municipality is found from the coordinate.
    radius_km:     Keep only pharmacies within this distance of lat/lon.
    on_duty_only:  Only pharmacies on the duty roster today.
    open_now_only: Only pharmacies open right now.
    limit:         Max pharmacies returned (default 20, max 100).

Input parameters:

- `city`
- `lat`
- `limit` (integer)
- `lon`
- `on_duty_only` (boolean)
- `open_now_only` (boolean)
- `radius_km`

### `find_medicine_near` (~218 tokens)

One-shot answer to "I need medicine X in city Y — what do I do?" in Portugal.

Runs medicine_availability(medicine) and pharmacies(city or lat/lon), and returns: the shortage
status (compact), the pharmacies on duty today and the ones open now (nearest first when
lat/lon are given), the help lines (Linha 1400, SNS 24, 112) and next steps. It never
says a pharmacy has the medicine: stock is not public.

Args:
    medicine: Brand name or active substance, e.g. "quetiapina", "Brufen 400".
    city:     Municipality or town, e.g. "Lisboa". Or give lat/lon instead.
    lat, lon: Optional user position (sorts pharmacies by distance).
    limit:    Max pharmacies returned (default 8).

Input parameters:

- `city`
- `lat`
- `limit` (integer)
- `lon`
- `medicine` (string, required)

### `medicine_help` (~74 tokens)

Verified help lines in Portugal for medicine problems: 112, SNS 24, Linha 1400, Infarmed.

Use when someone can't find a medicine, needs urgent advice, or asks who to call. Each
line has its number, what it is for, hours where published, and the page it was checked on.

### `fuel_prices` (~462 tokens)

Cheapest fuel stations in Portugal for one fuel type, cheapest first (official DGEG prices).

Use for "where is diesel/petrol/LPG cheapest in Lisboa / near me / in Braga?". Give an
area as a district, a municipality, or a point (lat + lon, with radius_km); with no area
it searches all of Portugal. Names are case- and accent-insensitive ("evora" works).

Args:
    fuel_type:    A DGEG fuel name or id, e.g. "Gasóleo simples" (regular diesel, 2101),
                  "Gasolina simples 95" (regular 95 petrol, 3201), "Gasolina 98", "GPL Auto"
                  (LPG), or plain words: "diesel", "petrol", "95", "98", "lpg", "cng".
                  See fuel_types() for the full list.
    district:     Portuguese district, e.g. "Lisboa", "Porto", "Faro".
    municipality: Municipality (concelho), e.g. "Sintra", "Vila Nova de Gaia". Overrides district.
    lat, lon:     A point (WGS84). Results get distance_km and are limited to radius_km.
    radius_km:    Search radius around lat/lon (default 10).
    brand:        Only this brand (substring match), e.g. "Galp", "Prio", "Intermarché".
    limit:        How many stations to return (default 10, max 50).

Each station: price_eur (per litre, or per kg/m3 for gas), brand, name, address,
municipality, distance_km (with lat/lon), coordinates and last_update (the station's
last price update). Also returns how many stations matched and the min/median/max price.
Always mention the source (DGEG) and the last_update when quoting prices.

Input parameters:

- `brand`
- `district`
- `fuel_type` (string, required)
- `lat`
- `limit` (integer)
- `lon`
- `municipality`
- `radius_km` (number)

### `fuel_station_detail` (~66 tokens)

Full details of one fuel station: every fuel it sells with price and last update,
opening hours, services (car wash, shop, tyre air...) and payment methods.

Use after fuel_prices, with a station `id` from its results.

Input parameters:

- `station_id` (integer, required)

### `fuel_types` (~62 tokens)

List DGEG fuel types (id, name, unit) and the districts accepted by fuel_prices.

Only needed when unsure which fuel name to pass; fuel_prices also understands
"diesel", "petrol", "95", "98", "lpg".

### `ev_chargers` (~397 tokens)

Public EV charging sites near a point in Portugal (MOBI.E network), nearest first,
with live status and the price the network publishes for each charging point.

Use for "where can I charge near X?", "fast chargers near me", "is there a free CCS
charger nearby?". Needs coordinates; if the user gives a place name, use known
coordinates for it. Covers mainland Portugal, Azores and Madeira.

Args:
    lat, lon:       Point to search around (WGS84).
    radius_km:      Search radius (default 5, max 100).
    min_power_kw:   Only points that can deliver at least this power, e.g. 50 for fast DC.
    connector:      "CCS" (CCS2), "Type 2", "CHAdeMO", "CEE", or "DC" / "AC".
    available_only: Only points whose live status is "available" right now.
    limit:          Max sites to return (default 10, max 50).

Each site: operator, address, distance_km, opening hours and its matching points, each
with status (available, in use, out of order...), max power, connectors and price
(per_kwh / per_minute / per_session in EUR, from the feed). IMPORTANT: these are the
charging operator's published fees and may not be the whole bill: see `price_note` and
tell the user. `data_freshness` says how old the inventory and live status are.
The first call of the day downloads ~220 MB from MOBI.E and can take 1-3 minutes.

Input parameters:

- `available_only` (boolean)
- `connector`
- `lat` (number, required)
- `limit` (integer)
- `lon` (number, required)
- `min_power_kw`
- `radius_km` (number)

### `ev_charger_detail` (~126 tokens)

Everything about one MOBI.E charging site: all its points with live status, power,
connectors and price, plus operator contact, opening hours and accepted authentication
(app, RFID card, credit card...).

Use after ev_chargers. Accepts a site_id (e.g. "EZC-AMD-00051"), a point_id
(e.g. "AMD-00051-1") or an EVSE id (e.g. "PT*EZC*E*AMD*00051*1").

Input parameters:

- `site_or_point_id` (string, required)

### `bus_find_stops` (~244 tokens)

Find Carris Metropolitana bus stops by name and/or near a coordinate.

Use this first whenever the user names a place, street, station or gives a location,
to get the stop_id needed by bus_next_arrivals. Results include the lines serving each stop.

Args:
    query:    Text to match in the stop name (accent/case-insensitive, all words must match),
              e.g. "Gare do Oriente", "Cacilhas terminal". A 6-digit stop id also works.
    lat, lon: A coordinate (WGS84). Results are sorted by straight-line distance from it.
              Note: buses inside Lisbon city are mostly run by Carris (a different
              company, not covered here); Carris Metropolitana serves the wider region.
    radius_m: Only stops within this many metres of lat/lon. Default 500 when no query is
              given; unlimited when a query is given.
    limit:    Max stops to return (default 10, max 50).

Input parameters:

- `lat`
- `limit` (integer)
- `lon`
- `query`
- `radius_m`

### `bus_next_arrivals` (~199 tokens)

Upcoming buses at a Carris Metropolitana stop, real-time where available.

Use for "when is the next bus at X?" (get stop_id from bus_find_stops first).
Each arrival says whether it is "realtime" (live GPS estimate) or "scheduled" (timetable
only: the bus may not have started its trip yet). minutes_from_now uses the real-time
estimate when present. Times are Europe/Lisbon. Only today's operational day is covered,
so late at night the list may be short or empty.

Args:
    stop_id: 6-digit stop id, e.g. "060361".
    line_id: Optional 4-digit line number to keep only that line, e.g. "2794".
    limit:   Max arrivals to return (default 10, max 50).

Input parameters:

- `limit` (integer)
- `line_id`
- `stop_id` (string, required)

### `bus_line_info` (~201 tokens)

Details of a Carris Metropolitana line: name, route ends, directions, municipalities.

Use for "where does line 4715 go?", "which bus goes from Cacilhas to Almada?", or to check
whether a line passes a stop (include_stops=True). If `line` is not an exact line number it
is treated as text (e.g. "Oriente Setubal") and the matching lines are listed instead.
trips_today = 0 means the line does not run today (some lines are seasonal or weekday-only).
Departure times past midnight are written "24:30", "25:10" (same service day).

Args:
    line:          4-digit line number ("4715") or free text matched against line names.
    include_stops: Also list every stop (id + name) in order for each direction.

Input parameters:

- `include_stops` (boolean)
- `line` (string, required)

### `bus_service_alerts` (~203 tokens)

Service alerts (detours, works, strikes, stops not served) for Carris Metropolitana.

Use before recommending a trip, or when the user asks "is line X disrupted?". Filter by
line and/or stop; with no filter, returns all current alerts (there are often ~100).
Alerts are mostly published in Portuguese only.

Args:
    line_id:          4-digit line number, e.g. "4407".
    stop_id:          6-digit stop id, e.g. "160584".
    include_upcoming: Also return alerts that start in the future (default True).
    language:         Preferred language ("pt" or "en"); falls back to what exists.
    limit:            Max alerts to return (default 20, max 100).

Input parameters:

- `include_upcoming` (boolean)
- `language` (string)
- `limit` (integer)
- `line_id`
- `stop_id`

### `bus_vehicle_positions` (~103 tokens)

Live GPS positions of the buses currently running on a Carris Metropolitana line.

Use for "where is the 3508 right now?" or to see how many buses are out on a line.
Each vehicle includes its position, heading, speed, the stop it is at / heading to,
and how many seconds old the fix is.

Args:
    line_id: 4-digit line number, e.g. "3508".

Input parameters:

- `line_id` (string, required)

### `transit_operators` (~24 tokens)

Which transport operators have timetables here, and what each one covers.

### `transit_find_stops` (~136 tokens)

Find train stations, metro stations or bus/tram stops by name, or the nearest to a point.

Args:
    query: e.g. "Oriente", "Porto Campanhã", "Marquês de Pombal", "Prazeres".
    operator: "cp", "metro_lisboa", "carris" or "fertagus". Default: all of them.
    lat, lon: find the nearest instead of (or as well as) by name.

Input parameters:

- `lat`
- `limit` (integer)
- `lon`
- `operator`
- `query`

### `transit_departures` (~194 tokens)

Scheduled departures from a station or stop (official timetable, not live).

Args:
    stop: station or stop name, e.g. "Lisboa Oriente", "Cais do Sodré", "Baixa-Chiado", "Prazeres".
    operator: "cp", "metro_lisboa", "carris" or "fertagus"; default: every operator that has the stop.
    when: ISO date-time in Lisbon time, e.g. "2026-11-03T08:00". Default: now.
    window_minutes: how far ahead to look (max 720).
    line: keep only a line or destination, e.g. "28E", "Sintra", "Azul".

Input parameters:

- `limit` (integer)
- `line`
- `operator`
- `stop` (string, required)
- `when`
- `window_minutes` (integer)

### `transit_trips_between` (~171 tokens)

Direct services between two stations (no changes), with departure, arrival and duration.

Examples: CP "Lisboa Oriente" → "Porto Campanhã"; Fertagus "Roma-Areeiro" → "Setúbal";
Metro "Alameda" → "Aeroporto" (same line only). Scheduled times, not live.
Args:
    operator: "cp", "metro_lisboa", "carris" or "fertagus"; default: try all.
    when: ISO date-time in Lisbon time; default now.
    window_minutes: departures within this window (max 1440).

Input parameters:

- `destination` (string, required)
- `limit` (integer)
- `operator`
- `origin` (string, required)
- `when`
- `window_minutes` (integer)

### `wildfires` (~224 tokens)

Burnt areas from wildfires in Portugal, mapped by satellite (EFFIS / Copernicus).

Not a live list of fires in progress: EFFIS maps burnt areas from satellite a day or more later,
and small fires can be missing.
Args:
    period: "today", "week", "month" or "season" (this year so far). Ignored when `year` is given.
    year: a past year from 2016, for the whole year.
    place: keep fires whose region or parish contains this, e.g. "Algarve", "Monchique", "Viseu".
    min_hectares: only fires at least this large.
    sort: "area" (largest first) or "date" (newest first).
    limit: max fires listed (totals always cover every match).

Input parameters:

- `limit` (integer)
- `min_hectares` (number)
- `period` (string)
- `place`
- `sort` (string)
- `year`

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/thiagojacoblannes-portugal-mcp/portugal-mcp#diagnostics

## Score history

- 2026-11-05: 61
- 2026-11-04: 76
- 2026-11-03: 76
- 2026-11-02: 61

## Common questions

### What is the Portugal (public data) MCP server?

Portugal (public data) is an MCP server listed in the public MCP registry as io.github.ThiagoJacobLannes/portugal-mcp. Portugal public data: IPMA weather, INE, Banco de Portugal, Parliament, contracts, SNS, fuel. This page covers its PyPI package (portugal-mcp).

### Is the Portugal (public data) MCP server safe to use?

Portugal (public data) scores 61 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. 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 Portugal (public data) MCP server expose?

Portugal (public data) exposes 47 tools: weather_forecast, weather_warnings, fire_risk, sea_forecast, earthquakes, and 42 more. Their descriptions and schemas cost roughly 8,005 tokens of context every time the server is loaded.

### Is the Portugal (public data) MCP server still maintained?

Portugal (public data) is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Portugal (public data) MCP server under?

Portugal (public data) declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Portugal (public data) MCP server?

VerifyMCP ran 14 checks on Portugal (public data), covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about Portugal (public data): Malware scan and Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/portugal-mcp/
- Socket report: https://socket.dev/pypi/package/portugal-mcp
- Repository: https://github.com/ThiagoJacobLannes/portugal-mcp
- Website: https://thiagolannes.com/
- Changelog RSS feed: https://verifymcp.io/servers/thiagojacoblannes-portugal-mcp/portugal-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/thiagojacoblannes-portugal-mcp/portugal-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/thiagojacoblannes-portugal-mcp/portugal-mcp.json
- HTML version of this page: https://verifymcp.io/servers/thiagojacoblannes-portugal-mcp/portugal-mcp