Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Swissyphus

OCI · GHCR.IO/CWELLBOURNEWOOD/SWISSYPHUS · 2 COMPONENTS

Swiss public-data rollup for AI agents: 151 tools, 66 sources, zero keys, every answer cited.

+3 this week 46 Trust /100

Last scanned (23 hours ago)

Scores higher than 50% of OCI servers

Category Data and Analytics

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security0
  • No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
  • Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 12 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability76
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 25136 tokens (~164/item across 153 items; 151 tools + 2 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 Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage93
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 78% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 151 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 153 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

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.

What we tested

Checks we ran (12)

  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (4)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  • Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  • Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
  • Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

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

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Nov 26 +1
    • Security disclosure: unverified → pass ▲ functional
  • 10 Nov 26 +6
    • Source repository: fail → pass ▲ security
  • 9 Nov 26 35

    First indexed and scored.

Diagnostics

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 · Analysed oci/ghcr.io/cwellbournewood/swissyphus@v1.0.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem oci
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 151 exposed · ~23,422 tokens

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 →

Tool Tokens
list_shared_mobility_providers ~128

All bike/e-bike/e-scooter/moped/car/cargo-bike sharing providers in the sharedmobility.ch national aggregator: provider_id, name, vehicle types, website and Android/iOS app links. Filter by name substring (query: 'publibike') or vehicle_type ('car'). Provider names match the 'provider' field of get_shared_vehicles_nearby.

NameTypeReqDescription
limitinteger––
querystring–Substring of provider name or id, e.g. 'mobility', 'voi'
vehicle_typestring––

No output schema declared.

No examples provided.

list_snb_datasets ~144

Curated list of well-known Swiss National Bank data-portal cube ids (FX rates, money market rates incl. SARON, Confederation bond yields, SNB balance sheet, monetary aggregates, CPI, effective exchange rates) with frequency and a confidence flag for each id. Optional keyword filter, e.g. 'saron', 'bond yield', 'balance sheet', 'M3'. Then call get_snb_cube_dimensions or get_snb_data with the cube_id. Any other cube id from data.snb.ch also works with those tools.

NameTypeReqDescription
querystring–Optional keywords, e.g. 'saron', 'inflation', 'bond'

No output schema declared.

No examples provided.

list_snow_stations ~96

List SLF IMIS high-alpine measurement stations with code, name, elevation and coordinates. Filter by canton or name, or sort by distance from a point.

NameTypeReqDescription
cantonstring–Canton code filter, e.g. 'GR', 'VS'
limitinteger––
near_latnumber––
near_lonnumber––
querystring–Name fragment filter

No output schema declared.

No examples provided.

list_sources ~41

The machine-readable register of every data source behind the active Swissyphus modules: operator, licence, attribution string, update frequency, cache TTL and caveats.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_vote_dates ~32

List available federal popular-vote days with official result data (newest first).

NameTypeReqDescription
limitinteger––

No output schema declared.

No examples provided.

list_waste_types ~22

All waste/recycling collection types supported by the waste calendar.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_weather_stations ~33

List official SwissMetNet stations reporting a given parameter, with coordinates and altitude.

NameTypeReqDescription
parameterstring––

No output schema declared.

No examples provided.

lookup_code_list ~157

Search the entries of an official Swiss code list on I14Y by code or text, e.g. NOGA industry classification ({codelist: 'NOGA_CLASS', query: 'bank'} or {codelist: 'NOGA_CLASS', query: '6419'}), NOGA levels NOGA_SECTION/NOGA_DIVISION/NOGA_GROUP/NOGA_CLASS/NOGA_TYPE, or any code list found with search_federal_metadata (pass its identifier or id).

NameTypeReqDescription
codeliststringyesCode list identifier (e.g. 'NOGA_CLASS') or concept id (UUID)
langstring––
limitinteger––
querystringyesCode or words to search for

No output schema declared.

No examples provided.

lookup_postcode ~52

Resolve a 4-digit Swiss postal code (PLZ/NPA) to its locality/localities with coordinates.

NameTypeReqDescription
plzstringyes4-digit Swiss postal code, e.g. '8001'

No output schema declared.

No examples provided.

lookup_uid ~155

Look up one entity in the federal UID register (BFS) by its UID — e.g. 'CHE-107.028.276', 'CHE107028276', '107028276' or a VAT number 'CHE-107.028.276 MWST'. Validates the check digit first (offline). Returns name, legal form, address, UID status, VAT register status (registered yes/no, VAT number, entry date) and commercial-register status. Covers ALL UID holders incl. associations, foundations, sole proprietors and public bodies that are not in ZEFIX.

NameTypeReqDescription
uidstringyesUID in any format, e.g. 'CHE-107.028.276' or '107028276'

No output schema declared.

No examples provided.

query_bfs_table ~276

Fetch labelled figures from any STAT-TAB table. 'selection' maps variables (code or label, case/accents ignored) to values (codes or labels); '*' = all values, 'latest' / 'latest:5' = last period(s), '2015-2020' = year range. Unspecified variables default to their total (e.g. 'Schweiz', 'Total') or the latest period, and the response lists every default applied. Max 5000 cells per query. Returns rows like {Kanton:'Zürich', value:1605508} plus 'fixed' for single-valued dimensions. Example: {table_id:'px-x-0102010000_101', selection:{Jahr:['latest'], Kanton:['Zürich','Bern'], Geschlecht:['*']}}.

NameTypeReqDescription
include_codesboolean–Also return value codes next to labels
langstring–Language of titles/labels: de, fr, it or en (default en)
limitinteger–Max rows returned
selectionobject–Map variable → values, e.g. {"Jahr": ["latest"], "Kanton": ["*"]}
table_idstringyesTable id like 'px-x-0102010000_101'

No output schema declared.

No examples provided.

query_data_cube ~320

Fetch observations from a LINDAS statistical cube as flat rows keyed by dimension labels (IRI values replaced by their human labels; numbers as numbers). Optional filters map a dimension (label, IRI or IRI local name) to one value or a list of values (label, literal such as a year, or IRI) — matching is exact and case-insensitive; get valid values from describe_data_cube. Returns columns (with role and unit), rows and row_count. limit default 100, max 1000 (large results are trimmed to fit 50 KB). Examples: {cube: 'https://energy.ld.admin.ch/elcom/electricityprice', filters: {'Period': '2025', 'Category': 'H4'}, limit: 50}, {cube: '<IRI>', filters: {'Canton': ['Zürich', 'Bern']}}.

NameTypeReqDescription
cubestringyesCube IRI from search_data_cubes
filtersobject–{dimension label/IRI: value label/IRI or array of them}. Max 10 filters.
include_irisboolean–Also return the raw IRI of each IRI-valued cell as '<column> IRI'
include_sparqlboolean–Return the generated SPARQL (to adapt with query_lindas)
langstring––
limitinteger––
offsetinteger–Skip observations for paging (stable order; max 10000 — use filters to reach deeper data)

No output schema declared.

No examples provided.

query_dataset ~553

Fetch the actual data of an opendata.swiss / City of Zürich dataset and return matching rows. Picks the best machine-readable resource (CSV > JSON > GeoJSON; HTML landing pages, ZIP, XLSX, PDF and services are skipped and reported with their download URLs), parses it and applies search / column filters / sort / paging. Returns columns, total matched, rows, the resource used and its licence. Works with a dataset id or a direct resource_url. Run describe_dataset_columns first to learn column names and values. Examples: {id: '<dataset-id>', where: {Kanton: 'ZH'}, sort: '-Einwohner', limit: 10}; {id: '<dataset-id>', search: 'Winterthur', columns: ['Jahr','Wert']}; {resource_url: 'https://…/data.csv', where: {Jahr: '>2020'}}.

NameTypeReqDescription
columnsarray–Only return these columns (names are matched case/accent-insensitively; max 50)
formatstring–Preferred resource format (overrides the CSV-first default)
idstring–Dataset ID (slug): the 'id' of a search_datasets hit
langstring–Language for titles/descriptions: de, fr, it or en (default en; falls back to de)
limitinteger–Rows to return (default 25, max 200; large rows are trimmed to fit 50 KB)
offsetinteger––
portalstring–Catalogue: 'opendata.swiss' (default, national), 'stadt-zuerich' (City of Zürich, data.stadt-zuerich.ch) or 'envidat' (WSL/ETH environmental research data: snow, glaciers, forests, biodiversity, clim…
resourcestring–Optional resource selector: 0-based index from get_dataset, resource id, or part of its title. Default: best CSV > JSON > GeoJSON
resource_urlstring–Alternatively, a direct https URL of a CSV/JSON/GeoJSON file (e.g. a download_url from get_dataset). May be disabled on public deployments — prefer 'id'
searchstring–Case-insensitive substring matched against every field
sortstring–Sort column; prefix '-' for descending, e.g. '-Jahr'
whereobject–Column filters: {column: value}. Exact (case-insensitive) match; prefix '~' for substring, '>'/'<' for numeric compare, e.g. {"Kanton": "ZH", "Jahr": ">2019"}

No output schema declared.

No examples provided.

query_layer_at_point ~409

Read the attributes of any federal map layers at a WGS84 location: point-in-polygon (radius_m=0), everything within a radius in metres (e.g. antennas within 300 m), or everything inside a bbox. Up to 15 layers per call; results grouped per layer, with per-layer errors isolated if a layer id is bad. Examples: layers='ch.bafu.laerm-strassenlaerm_tag,ch.bag.radonkarte', lat=46.948, lon=7.4474; layers='ch.bakom.standorte-mobilfunkanlagen', radius_m=300, return_geometry=true. Use search_map_layers to find layer ids; for a ready-made multi-layer summary use get_location_report.

NameTypeReqDescription
bboxarray–Alternative to lat/lon: WGS84 bbox [minLon,minLat,maxLon,maxLat], max ~5 km per side
langstring–Language for labels/attributes: de, fr, it, rm or en (default en)
latnumber–WGS84 latitude, e.g. 46.9480 (Switzerland ≈ 45.8–47.8)
layersstringyesComma-separated layer ids (max 15), e.g. 'ch.bafu.laerm-strassenlaerm_tag,ch.are.bauzonen'
lonnumber–WGS84 longitude, e.g. 7.4474 (Switzerland ≈ 5.9–10.5)
per_layer_limitinteger–Max features returned per layer (default 5)
radius_mnumber–Search radius in metres around lat/lon (0 = exactly at the point; max 2000)
return_geometryboolean–Include a WGS84 anchor point per feature (useful with radius/bbox)
time_instantinteger–Year for time-enabled layers (see get_layer_info)

No output schema declared.

No examples provided.

query_lindas ~133

Run a read-only SPARQL SELECT query against lindas.admin.ch, the Swiss federal linked-data service. Useful graphs include <https://lindas.admin.ch/elcom/electricityprice> (energy prices), ELI legislation, the municipality register (ld.admin.ch/municipality/{BFS}), and cube.link statistical cubes. A top-level LIMIT of 100 is added if none is given and larger limits are clamped to 200; SERVICE (federation) and update operations are rejected; max 10000 characters.

NameTypeReqDescription
querystringyesSPARQL SELECT query (read-only)

No output schema declared.

No examples provided.

query_portal_records ~577

Fetch records from a dataset on a Swiss Opendatasoft portal with ODSQL: where (e.g. "kanton = 'BS'", "jahr >= 2020", "search(name, 'Bahnhof')"), select (e.g. 'bahnhof_haltestelle, dtv, jahr'), order_by (e.g. 'dtv desc'), group_by with aggregates (select 'kanton, count(*) as n, sum(dtv) as total', group_by 'kanton'), limit/offset. Convenience `near` {lat, lon, radius_m} finds the dataset's geo_point_2d field and returns only records within the radius, sorted by distance (e.g. parking garages within 800 m of Basel SBB: portal 'basel-stadt', near {lat:47.5476, lon:7.5896, radius_m:800}). Real-time datasets (parking occupancy, SBB data) are cached only 10 min. Get field names first with get_portal_dataset.

NameTypeReqDescription
dataset_idstringyesDataset id from search_portal_datasets
geo_fieldstring–geo_point_2d field to use for `near` (auto-detected if omitted)
group_bystring–e.g. 'kanton' or 'year(datum)'; combine with aggregates in select
langstring–Language for localized values where the portal supports it
limitinteger–Records to return (max 100)
nearobject–Radius search around a WGS84 point, e.g. {lat: 47.5476, lon: 7.5896, radius_m: 500}
offsetinteger–Paging offset (offset + limit ≤ 10000)
order_bystring–e.g. 'dtv desc' or 'n desc'
portalstringyesPortal id, alias or domain: 'sbb' (data.sbb.ch), 'basel-stadt' (data.bs.ch), 'basel-landschaft' (data.bl.ch), 'st-gallen' (daten.sg.ch), 'stadt-st-gallen' (daten.stadt.sg.ch), 'graubuenden' (data.gr.…
selectstring–Fields/expressions to return, e.g. 'name, belegung, geo_point_2d' or 'kanton, count(*) as n'
wherestring–ODSQL filter, e.g. "jahr = 2023 AND dtv > 10000" (string literals in single or double quotes)

No output schema declared.

No examples provided.

query_wikidata ~197

Run a read-only SPARQL SELECT (or ASK) against the Wikidata Query Service. Prefixes wd:, wdt:, p:, ps:, pq:, rdfs:, schema:, wikibase:, bd: are predefined; use SERVICE wikibase:label { bd:serviceParam wikibase:language "de,fr,en". } for labels. Swiss hooks: wd:Q39 = Switzerland, wdt:P771 = BFS municipality code, wdt:P17 = country, wdt:P131 = located in. Example: SELECT ?m ?mLabel ?bfs WHERE { ?m wdt:P771 ?bfs . SERVICE wikibase:label { bd:serviceParam wikibase:language "de". } }. LIMIT 100 is injected when absent; larger LIMITs are clamped to 1000. 60 s timeout.

NameTypeReqDescription
querystringyesSPARQL SELECT/ASK query (read-only)

No output schema declared.

No examples provided.

read_geodata_asset ~340

Download a CSV or JSON asset from data.geo.admin.ch (href from get_geodata_collection_items) and return it as rows you can filter, sort and page — e.g. MeteoSwiss SwissMetNet station files. Filters: where={column: value} (exact), '~text' (substring), '>n'/'<n' (numeric). tail=true returns the latest rows of a time series. Example: url='https://data.geo.admin.ch/ch.meteoschweiz.ogd-smn/ber/ogd-smn_ber_d_recent.csv', tail=true, limit=7, columns=['reference_timestamp','tre200d0','rre150d0']. Large historical files may exceed max_mb — prefer '_recent' or '_now' files.

NameTypeReqDescription
columnsarray–Columns to return (default all; max 40)
limitinteger–Max rows (default 50)
max_mbnumber–Download size cap in MB (default 8, max 20)
offsetinteger–Skip this many matching rows (ignored with tail)
searchstring–Case-insensitive text search across all columns
sortstring–Sort column; prefix '-' for descending
tailboolean–Return the LAST matching rows (latest values of a time series)
urlstringyesAsset href on https://data.geo.admin.ch/ (CSV, TXT or JSON/GeoJSON)
whereobject–Column filters, e.g. {"station_abbr": "BER"} or {"tre200d0": ">25"}

No output schema declared.

No examples provided.

reverse_geocode ~95

Find the nearest registered building/address for WGS84 coordinates using the federal Register of Buildings and Dwellings (GWR). Returns street, number, postal code, locality, municipality and EGID.

NameTypeReqDescription
latnumberyesWGS84 latitude (Switzerland: ~45.8–47.9)
lonnumberyesWGS84 longitude (Switzerland: ~5.9–10.6)

No output schema declared.

No examples provided.

search_bfs_tables ~191

Find Federal Statistical Office (BFS) tables on STAT-TAB by keywords: population, births, deaths, migration, tourism overnight stays, crime, students, vehicles, buildings, enterprises and hundreds more. Returns table ids (e.g. 'px-x-0102010000_101') with titles, to pass to get_bfs_table_metadata then query_bfs_table. Titles are in the chosen language, so use matching search terms (e.g. lang='de', query 'Logiernächte Kanton'). Examples: {query:'population commune age'}, {query:'hotel overnight stays', lang:'en'}.

NameTypeReqDescription
langstring–Language of titles/labels: de, fr, it or en (default en)
limitinteger––
querystringyesKeywords, e.g. 'population canton', 'Straftaten', 'overnight stays'

No output schema declared.

No examples provided.

search_companies ~115

Search the Swiss commercial register (ZEFIX, 700k+ entities) by company name. Returns UID, legal form, seat, status and a link to the cantonal register excerpt. A UID like 'CHE-123.456.789' as query is looked up directly.

NameTypeReqDescription
cantonstring–Optional canton filter, e.g. 'ZH'
limitinteger––
offsetinteger–Pagination offset
querystringyesCompany name (or UID) to search for

No output schema declared.

No examples provided.

search_consultations ~131

Federal consultation procedures (Vernehmlassungen / consultations / consultazioni) on draft laws and ordinances from Fedlex: title, description, status (planned, ongoing, closed, withdrawn), consultation period and lead federal office, newest first. Use it to see what legislation the Federal Council is preparing and until when stakeholders can respond. Example: {query: 'Energie', status: 'ongoing'}.

NameTypeReqDescription
languagestring––
limitinteger––
querystring–Word in title or description (in the chosen language)
statusstring––

No output schema declared.

No examples provided.

search_council_members ~131

Search members of the National Council and Council of States (current by default) by last name (case-insensitive fragment), canton or party abbreviation.

NameTypeReqDescription
active_onlyboolean––
cantonstring–Canton abbreviation, e.g. 'ZH'
limitinteger––
namestring–Last-name fragment (case-insensitive)
partystring–Party abbreviation as used in German, case-insensitive, e.g. 'SVP', 'SP', 'FDP-Liberale', 'M-E', 'GRÜNE', 'glp'

No output schema declared.

No examples provided.

search_court_decisions ~318

Full-text search across Swiss court decisions aggregated by entscheidsuche.ch: Federal Supreme Court (BGer/BGE), Federal Administrative Court (BVGer), Federal Criminal Court (BStGer), Federal Patent Court and the courts of all 26 cantons. Returns docket/reference number, decision date, court, canton, title, abstract snippet, matching text excerpts and a link to the decision (PDF/HTML). Query syntax: words are AND-ed; use "quotes" for phrases, | for OR, - to exclude. Examples: query='Mietzins Kündigung' canton='ZH'; query='"Art. 336 OR"' court='BGer' date_from='2020'; query='5A_123/2020'.

NameTypeReqDescription
cantonstring–Canton code, e.g. 'ZH'; 'CH' = federal courts
courtstring–Court: 'BGer', 'BGE', 'BVGer', 'BStGer', 'BPatGer', or an index code like 'ZH_OG' / 'CH_BGer'
date_fromstring–Earliest decision date, e.g. '2020' or '2020-01-31'
date_tostring–Latest decision date
languagestring–Preferred language for titles/abstracts (boosted, not filtered)
limitinteger––
querystringyesSearch terms, a legal provision or a docket number
sortstring––

No output schema declared.

No examples provided.

search_cpv_codes ~94

Look up Common Procurement Vocabulary (CPV) codes by keyword or partial number, e.g. 'Strassenbau', 'software', '4523'. Use the 8-digit codes as `cpv_codes` in search_public_tenders.

NameTypeReqDescription
langstring–Language for titles and texts (falls back to the notice's original language)
limitinteger––
querystringyes–

No output schema declared.

No examples provided.

search_dams ~190

Search the federal dam register (SFOE, ~225 dams) by dam, reservoir or facility name, purpose (hydroelectricity, flood protection, irrigation, …) or dam type (arch, gravity, embankment, …), ranked by height, volume, crest length or year built. With no filters it ranks all dams, e.g. the tallest or largest. Examples: {query:'Dixence'}, {sort_by:'volume'}, {purpose:'flood'}.

NameTypeReqDescription
limitinteger––
orderstring––
purposestring–e.g. hydroelectricity, flood protection, irrigation, drinking water
querystring–Dam, reservoir or facility name (partial, accents optional)
sort_bystring––
typestring–e.g. arch, gravity, embankment, buttress

No output schema declared.

No examples provided.

search_data_cubes ~280

Keyword search over the federal statistical data cubes on LINDAS (the data behind visualize.admin.ch): electricity prices (ElCom), energy statistics (BFE), environment/air/water (BAFU), agriculture (FOAG), traffic counts (ASTRA), population and economy (BFS) and more. Every word must appear (case-insensitive) in the cube's name, description, publisher or IRI, in any language (German terms often match best, e.g. 'Strompreis', 'Luft', 'Verkehr'). Returns cube IRI, name, trimmed description, publisher, last-modified date and a visualize.admin.ch link. Deprecated cube versions are excluded; published cubes shown on visualize.admin.ch rank first. Next step: describe_data_cube {cube: <IRI>}. Examples: {query: 'electricity price'}, {query: 'Treibhausgas', lang: 'de'}, {query: 'bfe energie', limit: 10}.

NameTypeReqDescription
langstring–Preferred language for names/descriptions (falls back to de/fr/it/en)
limitinteger––
offsetinteger––
published_onlyboolean–Exclude cubes whose status is Draft
querystring–Keywords (all must match). Empty lists the most recently modified cubes.

No output schema declared.

No examples provided.

search_datasets ~426

Full-text search over the national open-data catalogue opendata.swiss (default) or the City of Zürich portal (portal='stadt-zuerich'): statistics (population, prices, energy…), geodata, transport, health and more. Each hit lists its resource formats and whether it is queryable (has CSV/JSON/GeoJSON). Filter by publisher (slug from list_data_publishers), by format (e.g. 'CSV'), sort by 'modified' for the newest. Then call query_dataset {id} for the actual rows, or get_dataset {id} for metadata. Examples: {query: 'Mietpreisindex'}, {query: 'Bevölkerung Gemeinde', format: 'CSV'}, {publisher: 'bundesamt-fur-statistik-bfs', sort: 'modified'}, {query: 'Velo', portal: 'stadt-zuerich'}.

NameTypeReqDescription
formatstring–Only datasets with a resource of this format, e.g. 'CSV', 'JSON', 'GeoJSON', 'XLSX'
langstring–Language for titles/descriptions: de, fr, it or en (default en; falls back to de)
limitinteger––
offsetinteger–Skip this many hits (paging)
portalstring–Catalogue: 'opendata.swiss' (default, national), 'stadt-zuerich' (City of Zürich, data.stadt-zuerich.ch) or 'envidat' (WSL/ETH environmental research data: snow, glaciers, forests, biodiversity, clim…
publisherstring–Optional publisher (organization) slug, e.g. 'bundesamt-fur-statistik-bfs' — see list_data_publishers
querystring–Search terms, e.g. 'rent index', 'STATPOP', 'Luftqualität'. German terms match best. Optional if publisher/format is given
sortstring–relevance (default), modified (newest updates first), created, name

No output schema declared.

No examples provided.

search_earthquakes ~131

Search historical seismic events near a WGS84 point within a radius, with optional date range (inclusive; date_to covers the whole day) and magnitude filter.

NameTypeReqDescription
date_fromstring–Start date YYYY-MM-DD (default: 1 year back)
date_tostring–End date YYYY-MM-DD (inclusive)
latnumberyesWGS84 latitude of search centre
limitinteger––
lonnumberyesWGS84 longitude of search centre
min_magnitudenumber––
radius_kmnumber––

No output schema declared.

No examples provided.

search_federal_gazette ~228

Search publications in the Federal Gazette (Bundesblatt BBl / Feuille fédérale FF / Foglio federale FF): Federal Council dispatches (Botschaften) on new bills, draft federal acts and decrees, referendum texts, reports and official notices. Filter by title keyword and publication-date range; returns date, title, BBl reference (e.g. 'BBl 2024 1234') and Fedlex link, newest first. Examples: {query:'Botschaft'}; {query:'Klima', date_from:'2023-01-01'}; {query:'énergie', language:'fr'}.

NameTypeReqDescription
date_fromstring–Earliest publication date (default: 90 days before date_to, or 2 years with a query; range max 2 years)
date_tostring–Latest publication date (default: today)
languagestring––
limitinteger––
querystring–Title keyword in the chosen language, e.g. 'Botschaft', 'Datenschutz'

No output schema declared.

No examples provided.

search_federal_law ~137

Search the Swiss Classified Compilation (SR/RS) of federal law by title or abbreviation (e.g. 'data protection', 'OR', 'Datenschutz'). Exact abbreviation/title matches are ranked first. Returns SR number, title, abbreviation and the official Fedlex link. Search in the language of your query term (German titles for German terms, etc.).

NameTypeReqDescription
in_force_onlyboolean––
languagestring–Language of titles to search
limitinteger––
querystringyesTitle keyword or abbreviation, e.g. 'Datenschutz', 'obligations', 'DSG'

No output schema declared.

No examples provided.

search_federal_metadata ~149

Search I14Y, the Swiss federal interoperability platform: datasets (incl. non-public registers, with their access rights), data services/APIs, public services and concepts/code lists from federal, cantonal and municipal bodies. Use it to find which authority holds what data, or the identifier of an official code list. Example: {query: 'NOGA', types: ['Concept']}, {query: 'Gebäude', types: ['Dataset']}.

NameTypeReqDescription
langstring––
limitinteger––
querystringyes–
typesarray–Restrict to Dataset, DataService, Concept (incl. code lists), PublicService, MappingTable

No output schema declared.

No examples provided.

search_geodata_collections ~212

Keyword search over the downloadable federal geodata collections on data.geo.admin.ch (STAC): swisstopo elevation/imagery/maps, BAFU/BFE/ARE datasets and MeteoSwiss open data — e.g. 'ch.meteoschweiz.ogd-smn' (SwissMetNet automatic weather stations), 'ch.meteoschweiz.ogd-nime' (manual precipitation), 'ch.meteoschweiz.ogd-pollen'. Returns collection ids, titles, licence, providers and time extent. Next: get_geodata_collection_items. Examples: query='meteoschweiz', 'swissalti3d', 'Lärm'. Omit query to page through all collections.

NameTypeReqDescription
limitinteger–Max collections (default 20)
offsetinteger–Skip this many matches (paging)
querystring–Keywords matched against id, title, description, keywords and providers (all must match)

No output schema declared.

No examples provided.

search_international_treaties ~237

Search international treaties and agreements binding Switzerland (the international part of the Classified Compilation, SR numbers starting '0.': bilateral agreements with the EU, double-taxation agreements, conventions, UN/Council of Europe treaties) by title keyword and/or SR area. Returns SR number, title, short title, entry-into-force date, in-force status and the Fedlex link. Titles are language-specific: {query:'Doppelbesteuerung'} (de), {query:'double imposition', language:'fr'}, {query:'Freizügigkeit'}, {sr_prefix:'0.142.11'} (EU free movement area).

NameTypeReqDescription
in_force_onlyboolean––
languagestring–Language of titles to search
limitinteger––
querystring–Title keyword in the chosen language, e.g. 'Doppelbesteuerung', 'Deutschland', 'Menschenrechte'
sr_prefixstring–Restrict to an SR area of international law, e.g. '0.1' (international law), '0.672' (double taxation)

No output schema declared.

No examples provided.

search_library_catalogue ~155

Search the swisscovery union catalogue of Swiss academic libraries by keywords, title, author, subject or ISBN (fields are combined with AND). Returns bibliographic records (title, creators, publisher, year, ISBN, subjects, online links) and a swisscovery link to check holdings/availability. Example: {author: 'Spyri', title: 'Heidi'}, {subject: 'Gletscher', keywords: 'Klimawandel'}.

NameTypeReqDescription
authorstring––
isbnstring––
keywordsstring–Free-text keywords (all fields)
limitinteger––
offsetinteger––
subjectstring––
titlestring––

No output schema declared.

No examples provided.

search_local_parliament_business ~178

Search motions, postulates, interpellations, questions and bills in cantonal and municipal parliaments, newest first. Filter by parliament (body_key) and text. Example: {query: 'Velo', body_key: 'ZH'} or {body_key: '261'} for the latest business of Zürich city parliament.

NameTypeReqDescription
body_keystring–Parliament: canton code ('ZH', 'VD') or BFS municipality number ('261' = City of Zürich); see search_local_parliaments
full_textboolean–Also search in documents and texts (slower)
langstring––
limitinteger––
offsetinteger––
querystring–Words in the title/metadata, e.g. 'Tempo 30', 'Wohnungsnot'

No output schema declared.

No examples provided.

search_local_parliaments ~131

Find Swiss cantons, cities and municipalities in OpenParlData and whether their parliament is covered; returns the body_key used by the other local-politics tools. Example: {query: 'Winterthur'} or {canton: 'BE', with_parliament: true}.

NameTypeReqDescription
cantonstring–Only bodies in this canton
langstring––
limitinteger––
querystring–Name of a canton, city or municipality
typestring––
with_parliamentboolean–Only bodies whose parliament data is covered

No output schema declared.

No examples provided.

search_local_politicians ~121

Find members of cantonal and municipal parliaments by name, optionally in one parliament: party, electoral district, occupation. Example: {query: 'Meier', body_key: 'ZH'}.

NameTypeReqDescription
body_keystring–Parliament: canton code ('ZH', 'VD') or BFS municipality number ('261' = City of Zürich); see search_local_parliaments
langstring––
limitinteger––
offsetinteger––
querystring–Name or part of it

No output schema declared.

No examples provided.

search_locality ~50

Search Swiss localities by name in the official directory and return their postal code(s).

NameTypeReqDescription
limitinteger––
namestringyesLocality name, e.g. 'Winterthur'

No output schema declared.

No examples provided.

search_map_layers ~189

Full-text search over the ~900 federal map layers on geo.admin.ch (noise, natural hazards, radon, zoning, protected areas, energy, transport, geology, …). Returns layer ids (e.g. 'ch.bafu.laerm-strassenlaerm_tag') with titles. Next: get_layer_info for fields/metadata, or query_layer_at_point to read values at a location. Examples: query='Strassenlärm', 'radon', 'Grundwasserschutz', 'solar', 'Bauzonen'.

NameTypeReqDescription
langstring–Language for labels/attributes: de, fr, it, rm or en (default en)
limitinteger–Max layers (default 15, max 30)
querystringyesKeywords (any national language or English), e.g. 'noise', 'Hochwasser', 'antennas'

No output schema declared.

No examples provided.

search_parliament_business ~97

Search Curia Vista for federal parliamentary business (motions, postulates, interpellations, bills) by title keyword (case-insensitive). Returns business number, type, status and submission date.

NameTypeReqDescription
languagestring–Language of titles searched (DE has best coverage)
limitinteger––
querystringyesKeyword to search in business titles, e.g. 'Klimaschutz', 'AI'

No output schema declared.

No examples provided.

search_parliament_speeches ~345

Search the verbatim record of speeches in the National Council and Council of States (Amtliches Bulletin transcripts) by speaker and/or keyword, optionally within a date range or session. Returns speaker, function, parliamentary group, canton, council, date, the business debated (short number + title when resolvable), a plain-text excerpt centred on the keyword, and a link to the official Bulletin debate. Keyword matching is case-sensitive and matches the speech's original language (e.g. 'Klimaschutz', 'Neutralität', 'intelligence artificielle'). Examples: {speaker:'Noser', keyword:'Datenschutz'}; {keyword:'Kita', date_from:'2024-01-01'}; {person_number:4057}. Speaker names come from search_council_members.

NameTypeReqDescription
date_fromstring–Earliest meeting date, YYYY-MM-DD
date_tostring–Latest meeting date, YYYY-MM-DD
excerpt_charsinteger–Max characters of speech text per result
keywordstring–Case-sensitive word/phrase in the speech text, in the language it was spoken, e.g. 'Klimaschutz'
languagestring–Language of labels such as council name (speech text stays in its original language)
limitinteger––
person_numberinteger–Exact PersonNumber of a council member (from search_council_members ID)
session_idinteger–Session ID from get_session_schedule (field ID)
speakerstring–Fragment of the speaker's full name, e.g. 'Noser', 'Funiciello'

No output schema declared.

No examples provided.

search_portal_datasets ~253

Full-text search of dataset catalogues on SBB and cantonal/city Opendatasoft portals — one portal or all in parallel (per-portal errors are reported, not fatal). Returns portal, dataset_id, title, short description, record count, last-modified date and themes; pass portal + dataset_id to get_portal_dataset / query_portal_records. Examples: {query:'passagierfrequenz', portal:'sbb'} (passengers per station), {query:'rollmaterial', portal:'sbb'}, {query:'Parkhaus'} (real-time parking), {query:'Rhein Temperatur', portal:'basel-stadt'}, {query:'Wahlen'}. Metadata is mostly German — use German terms. Omit query (with a portal) to list its most recently modified datasets.

NameTypeReqDescription
limitinteger–Max results per portal (capped at 15 when searching all portals)
portalstring–Optional portal (id/alias/domain). Omit to search all registered portals in parallel.
querystring–Search terms, e.g. 'Parkhaus', 'Luftqualität', 'Haltestellen', 'Bevölkerung'

No output schema declared.

No examples provided.

search_public_tenders ~344

Search procurement projects on simap.ch (Confederation, cantons, municipalities, public companies). Filter by text, cantons of performance, project type, latest notice type (e.g. 'tender' = open calls, 'award_tender' = awarded contracts) and publication date. Needs `query` (3+ chars) or at least one filter. Results are newest first; pass `next_cursor` back as `cursor` for the next page. Example: {query: 'Schulhaus', cantons: ['ZH'], notice_types: ['tender']}.

NameTypeReqDescription
cantonsarray–Cantons where the contract is performed, e.g. ['ZH','AG']
cpv_codesarray–8-digit CPV codes (see search_cpv_codes), e.g. ['45233140']
cursorstring–Pagination cursor (`next_cursor` from the previous page)
langstring–Language for titles and texts (falls back to the notice's original language)
notice_typesarray–Type of the newest notice: tender (open call), award_tender (award), direct_award, advance_notice, revocation, …
project_typesarray–construction | service | supply | *_competition | *_study | request_for_information
published_fromstring–Newest notice on/after this date (YYYY-MM-DD)
published_untilstring–Newest notice on/before this date (YYYY-MM-DD)
querystring–Search text (title, description), e.g. 'Reinigung', 'Software', 'Brücke'

No output schema declared.

No examples provided.

search_sanctions_list ~259

Screen a person, company or vessel name against the Swiss consolidated sanctions list (SECO, all embargo programmes: Russia/Ukraine, Belarus, Iran, Syria, North Korea, ISIL/Al-Qaida, …). Matching is case- and diacritic-insensitive over primary names, aliases and Latin transliterations; all query words must match (as words or word prefixes). Returns current listings only unless include_delisted=true. A hit is a lead, not a legal determination: compare birth dates, nationality and documents via get_sanctions_entry. Example: {name: 'Rotenberg'}, {name: 'Aeroflot', type: 'entity'}.

NameTypeReqDescription
include_delistedboolean–Also return entries that have since been de-listed
limitinteger––
namestringyesName or name fragment, e.g. 'Arkady Rotenberg', 'Sovcomflot'
programstring–Restrict to a sanctions programme, e.g. 'Ukraine', 'Iran', 'Syria' (see list_sanctions_programs)
typestring–Restrict to individuals, entities (companies/organisations) or objects (vessels, aircraft)

No output schema declared.

No examples provided.

search_sogc_publications ~145

Search official Swiss Official Gazette of Commerce (SOGC/SHAB) publications: commercial-register mutations (HR), bankruptcies (KK), debt enforcement, and more. Filter by keyword, rubric and date range. Results are listed newest first.

NameTypeReqDescription
date_fromstring–Earliest publication date YYYY-MM-DD
date_tostring–Latest publication date YYYY-MM-DD
keywordstring–Free-text keyword, e.g. a company name
limitinteger––
rubricstring–Rubric: HR=commercial register, KK=bankruptcy, LS=debt call, ES=inheritance, …

No output schema declared.

No examples provided.

search_stations ~45

Search Swiss public transport stations and stops by name.

NameTypeReqDescription
limitinteger––
querystringyesStation name or fragment, e.g. 'Interlaken'

No output schema declared.

No examples provided.

search_uid_register ~165

Search the federal UID register (BFS) by entity name — covers every UID holder (companies, associations, foundations, sole proprietors, public administrations), not just commercial-register entries. Optionally narrow by canton ('ZH') or postcode ('8001'); these filters are applied to the returned candidates. Returns UID, name, legal form, address, VAT and commercial-register status. Example: name='Pro Natura', name='Gemeinde Köniz'.

NameTypeReqDescription
cantonstring–Optional canton filter, e.g. 'BE'
limitinteger––
namestringyesEntity name or fragment, e.g. 'Migros', 'Verein Pro Velo'
postcodestring–Optional Swiss postcode filter, e.g. '3001'

No output schema declared.

No examples provided.

search_wikidata ~205

Find Wikidata items (Q-ids) by name — the universal join key for Swiss municipalities, cantons, mountains, lakes, rivers, companies, people and institutions. Returns id, label, description and match. Set swiss_only=true to keep only items whose country (P17) or citizenship (P27) is Switzerland (Q39). Examples: 'Matterhorn', 'Lac Léman', 'Nestlé', 'ETH Zürich', 'Winterthur' (swiss_only=true). Follow up with get_wikidata_entity.

NameTypeReqDescription
languagestring–Search/label language: de, fr, it, rm or en (default en)
limitinteger–Max results (1-50, default 10)
querystringyesName or label to search, e.g. 'Matterhorn', 'Roche', 'Aare'
swiss_onlyboolean–Restrict to items with country or citizenship = Switzerland

No output schema declared.

No examples provided.

track_parcel ~73

Generate the official Swiss Post tracking URL for a shipment number (parcels, registered mail). Returns the link — tracking status itself requires the Swiss Post site.

NameTypeReqDescription
tracking_numberstringyesSwiss Post shipment number, e.g. '99.60.126xxx.xxxxxxxx' or 'RX...CH'

No output schema declared.

No examples provided.

Install

How do I install the Swissyphus MCP server?

Swissyphus runs locally as a container image, launched with docker run --rm -i ghcr.io/cwellbournewood/swissyphus:v1.0.1 --stdio. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/cwellbournewood/swissyphus

# add to Claude Code
claude mcp add cwellbournewood-swissyphus -- docker run --rm -i ghcr.io/cwellbournewood/swissyphus:v1.0.1 --stdio
Common questions

What is the Swissyphus MCP server?

Swissyphus is an MCP server listed in the public MCP registry as io.github.cwellbournewood/swissyphus. Swiss public-data rollup for AI agents: 151 tools, 66 sources, zero keys, every answer cited. This page covers its container image (ghcr.io/cwellbournewood/swissyphus).

Is the Swissyphus MCP server safe to use?

Swissyphus scores 46 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 Swissyphus MCP server expose?

Swissyphus exposes 151 tools: search_companies, get_company, list_legal_forms, list_cantons, search_sogc_publications, and 146 more. Their descriptions and schemas cost roughly 23,422 tokens of context every time the server is loaded.

Is the Swissyphus MCP server still maintained?

Swissyphus 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 licence is the Swissyphus MCP server under?

Swissyphus 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 Swissyphus MCP server?

VerifyMCP ran 12 checks on Swissyphus, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about Swissyphus: Malware scan, Known CVEs, Install scripts and Dependency health. 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 container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.