bag-health-mcp
This read-only MCP server gives AI models access to Swiss public health data — BAG infectious-disease surveillance (51 pathogens), plus Obsan/Versorgungsatlas/Sucht Schweiz health indicators — for situational awareness and trends.
Discover disease topics:
bag_health_mcp__list_diseasesreturns all 51 BAG IDD topics (influenza, COVID-19, measles, wastewater, etc.) grouped by category.Find data series:
bag_health_mcp__list_serieslists series IDs for a disease (e.g. weekly cases vs. yearly incidence).Inspect filter options:
bag_health_mcp__get_series_detailsshows valid cantons, age groups, and sex values for a series before querying.Fetch surveillance data:
bag_health_mcp__get_disease_datareturns weekly/yearly counts or incidence rates, filterable by canton, age, sex, and time range.Get a canton overview:
bag_health_mcp__get_canton_situationproduces a one-call situational summary for a canton (e.g. ZH), aimed at school authorities and city administration.Bulk export access:
bag_health_mcp__list_export_filesandbag_health_mcp__download_exportlist and retrieve full CSV/JSON datasets per disease.Check data freshness:
bag_health_mcp__get_data_versionreturns the current weekly data snapshot date.Search health indicators:
bag_health_mcp__search_health_indicatorsqueries Obsan, Versorgungsatlas, and Sucht Schweiz (HBSC) by source, topic, region, and year.Retrieve indicator series:
bag_health_mcp__get_indicator_seriesfetches a national or cantonal indicator time series with 95% CIs and labels which statistical cut (variant) it returned.Read-only and safe: all tools are read-only, idempotent, non-destructive, and limited to three allow-listed public data hosts; responses carry provenance/attribution and aggregate-statistics notices.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@bag-health-mcp How is the flu evolving in Bern this week?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
bag-health-mcp
Part of the Swiss Public Data MCP Portfolio — connecting AI models to Swiss public data sources.
MCP server for Swiss public health data. Its core is the Swiss Federal Office of Public Health (BAG) Infectious Disease Dashboard (IDD) — epidemiological surveillance for 51 pathogens (influenza, COVID-19, measles, wastewater surveillance, and more) — extended with a multi-source health-indicator layer over the Swiss Health Observatory (Obsan), the Versorgungsatlas (health-care supply atlas, with cantonal series) and Sucht Schweiz (HBSC youth survey). All read-only, public Open Government Data.
What You Can Do
"Wie ist die aktuelle Grippesituation im Kanton Zürich verglichen mit den letzten Wochen?"
→ bag_health_mcp__get_canton_situation(canton="ZH")
"Gibt es aktuell einen Masernausbruch in der Schweiz?"
→ bag_health_mcp__get_disease_data(series_id="measles/cases/incValue/year", canton="all")
"Wie entwickelt sich das SARS-CoV-2-Signal im Abwasser?"
→ bag_health_mcp__list_series(topic="wastewater_viral_load")
→ bag_health_mcp__get_disease_data(series_id="wastewater_viral_load/NA/value/date", ...)
"Welche Krankheitsdaten stellt das BAG aktuell bereit?"
→ bag_health_mcp__list_diseases()
"Wie hat sich der Alkoholkonsum bei 15-Jährigen seit 2010 entwickelt?" # 🎯 anchor query
→ bag_health_mcp__search_health_indicators(source="suchtschweiz", topic="alkohol")
→ bag_health_mcp__get_indicator_series(source="suchtschweiz",
indicator_id="monam/alkoholkonsum-alter-11-15", region="ZH", year_from=2010)
→ More use cases by audience →🎯 Anchor demo query — «Wie hat sich der Alkoholkonsum bei 15-Jährigen im Kanton Zürich seit 2010 entwickelt, und wie steht der Kanton im Schweizer Vergleich da?» The HBSC youth series (via Obsan) answers the Switzerland-wide trend since 2010 with 95% confidence intervals. This particular indicator is national only, so the response includes a
region_notesaying so (HBSC is not cantonally representative). Most other Obsan indicators are published by canton — see the note on cuts below. These are aggregated population statistics — not individual advice. Seedocs/tool-design-health-indicators.md.
Related MCP server: swisstopo-mcp
Tools
Infectious-disease surveillance (BAG IDD):
Tool | Description |
| List all 51 disease topics, grouped by category |
| List data series for a specific disease |
| Get available filter dimensions (canton, age, sex) |
| Fetch time-series surveillance data |
| Situational overview for a canton (Schulamt use case) |
| List available complete export datasets |
| Download raw CSV/JSON export |
| Current data version (updated every Wednesday) |
Health indicators — Obsan, Versorgungsatlas & Sucht Schweiz (multi-source):
Tool | Description |
| Search indicators by |
| Fetch one indicator's time series, naming which cut it is ( |
⚠️ Aggregated population statistics only. The indicator tools serve population-level aggregates (prevalences/metrics by age/sex/region) — not individual advice, diagnosis or case assessment, and no personal data. This is stated in both tool descriptions and every response (
aggregate_statistics_notice), and matters especially forsuchtschweiz(HBSC), which touches prevention topics in a school context. Sources: Obsanind.obsan.admin.ch(clean JSON API); Sucht Schweiz HBSC via the Obsan mirror (national); Versorgungsatlas returns a cantonal year/value series (26 cantons + aCHnational total, with 95% CIs and a canton-vs-CH ratio) from the Tarifpool. See the per-source probe notes.
Obsan publishes an indicator in several cuts, not one series. Measured over 60 catalogue entries on 2026-08-08: 50 have a cantonal cut (
kg), 49 one by age class (ag), 24 one by social position (sd) — and only 3 the plain national one (g). They are different measurements with different units, soget_indicator_seriesnames the cut it returned invariantand lists the rest invariants_available, rather than presenting one as a stand-in for another. Eight of the 60 publish no series at all; that case fails with its reason instead of returning an empty result. The census is recorded and dated intests/fixtures/obsan_variant_census.json.
Tool annotations
All tools carry MCP tool annotations so a host can reason about them without calling. Every tool is identical here — it only ever reads from the public, allow-listed data sources (BAG IDD, Obsan, Versorgungsatlas):
Annotation | Value | Meaning |
|
| No tool mutates any state. |
|
| No destructive side effects. |
|
| Repeating a call has no additional effect. |
|
| Tools reach an external system (the upstream data APIs). |
A host may therefore treat all calls as safe, cacheable reads. The values are
declared once as READ_ONLY in server.py and applied to all 10 tools.
MCP Primitives
This server uses all three MCP primitives, each for what it is best at:
Tools (10) — live, parameterised actions that call the IDD API (above).
Resources — static, read-only reference data a host can fetch and cache, no arguments or upstream call needed:
Resource URI | Description |
| Canton codes accepted by the tools (incl. FL, |
| Disease-topic taxonomy by category |
| Source, attribution and licence terms |
Prompts — reusable, parameterised workflows a host can surface (e.g. as slash-commands):
Prompt | Arguments | Purpose |
|
| Draft a Schulamt public-health situation brief |
|
| Check whether a disease is currently elevated |
Live surveillance data stays behind Tools (it is parameterised and changes weekly); fixed reference data is exposed as Resources; recommended multi-tool workflows are packaged as Prompts.
Relevance for Schools & City Administration
Schulamt / Kreisschulbehörden:
Monitor influenza and ARI incidence in your canton
Single measles case → alert for schools with low vaccination coverage
Pertussis tracking → protect unvaccinated infants (siblings of school children)
Stadtverwaltung / KI-Fachgruppe:
Public Health Reporting with structured weekly data
Wastewater surveillance as 1-week lead indicator before clinical cases
Synergy with portfolio:
bag-epl-mcp→ "What treatments are listed?" (EPL medication database)bag-health-mcp→ "What is currently spreading?" (surveillance data)
Data Source
IDD API:
https://api.idd.bag.admin.ch— No authentication requiredUpdate cycle: Every Wednesday
Coverage: Switzerland + Liechtenstein (FL), 26 cantons
Topics: 51 pathogens, 1386 data series
Datenquellen & Lizenzen / Data sources & licences
Source | Provider | Licence | Attribution required |
Infectious Disease Dashboard (IDD) | Federal Office of Public Health (FOPH / BAG) | opendata.swiss Open Government Data — free use, source attribution required (Swiss OGD terms, CC BY-equivalent) | Yes |
Health indicators | Obsan — Swiss Health Observatory ( | No explicit machine-readable licence; treat as Swiss OGD practice — free use, cite the per-indicator source | Yes |
Health-care supply atlas | Versorgungsatlas (BAG/Obsan, | Same (Swiss OGD practice, cite source) | Yes |
HBSC youth survey | Sucht Schweiz — HBSC, obtained via the Obsan mirror | Same (Swiss OGD practice, cite «Sucht Schweiz — HBSC») | Yes |
Required citation: Federal Office of Public Health FOPH — Infectious Disease
Dashboard (IDD), open data via opendata.swiss. For the indicator tools, each
response's provenance.source names the concrete upstream (e.g. «Sucht Schweiz —
HBSC» via Obsan). Every tool response carries attribution in a provenance block
(attribution + license fields) so downstream consumers can surface it
automatically.
Architecture:
┌─────────────────┐ api.idd.bag.admin.ch (IDD API, no auth)
MCP Host │ bag-health-mcp │──▶ ind.obsan.admin.ch (Obsan JSON API)
(Claude, etc.) ──▶│ MCP SDK │──▶ versorgungsatlas.ch (indicator catalogue)
│ 10 Tools │ all HTTPS, egress allow-listed, no auth
└─────────────────┘Installation
Claude Desktop (stdio)
{
"mcpServers": {
"bag-health": {
"command": "uvx",
"args": ["bag-health-mcp"]
}
}
}Cloud / HTTP
pip install bag-health-mcp
python -m bag_health_mcp.server --http --port 8000Transport, host and port are set via environment variables — MCP_TRANSPORT
(http/stdio), MCP_HOST, MCP_PORT — which is the recommended way for
deployments (the --http flag still works for local use). The server binds to
127.0.0.1 by default so a local HTTP server is not exposed to the network.
Container/cloud deployments bind all interfaces by setting MCP_HOST=0.0.0.0
explicitly — the provided Dockerfile does this.
⚠️ Security: HTTP transport exposes the server on the network. Only bind beyond
127.0.0.1in a network-isolated environment — never directly on a public/shared network. Binding to a non-localhost host logs a warning at startup. The default stdio transport has no network surface. Seedocs/security-posture.md.
HTTP auth (optional): set MCP_AUTH_TOKEN to require
Authorization: Bearer <token> on every HTTP request (401 otherwise). Unset =
no auth (fine for stdio/local). This gates who may invoke the server; for real
user identity, front it with a gateway.
CORS (browser clients): set MCP_CORS_ORIGINS to a comma-separated origin
allow-list to enable cross-origin browser access. The 2026-07-28 routing
headers (Mcp-Method, Mcp-Name, Mcp-Protocol-Version) pass the preflight;
no session header is exposed, because the server issues none. Empty = no
cross-origin (never a wildcard).
Host allow-list (DNS rebinding): set MCP_ALLOWED_HOSTS to a comma-separated
list of the names this server is reachable under, including the port, e.g.
bag.example.ch:8000. Requests arriving under any other Host are rejected
with 421; loopback stays allowed so container health checks keep working.
Unset on a non-localhost bind, the check is left off and a warning is logged —
that is the gateway-fronted deployment, where the gateway validates Host. It
is not guessed: on 0.0.0.0 the reachable name is unknowable here, and a wrong
guess would reject the very deployment it is meant to protect.
This is independent of MCP_AUTH_TOKEN. The token says who is asking; this
says under which name the server is addressed. A rebinding attack runs in a
browser that already holds the token.
For running at scale (no session affinity needed, resource limits, MCP gateway), see the
deployment & scaling guide and the reference
manifests in deploy/.
Logging: the server emits structured JSON logs (one object per line, with an
RFC 5424 severity) to stderr — stdout is reserved for the stdio JSON-RPC
transport. Set the level with MCP_LOG_LEVEL (default INFO).
Tracing (optional): install the telemetry extra and point the server at an OTLP collector to get OpenTelemetry spans per tool-call plus instrumented outbound HTTP:
pip install "bag-health-mcp[telemetry]"
export OTEL_EXPORTER_OTLP_ENDPOINT="http://otel-collector:4318"
# optional: OTEL_SERVICE_NAME=bag-health-mcpTracing is a no-op unless both the extra is installed and an OTEL_*
endpoint is set. Spans carry only the tool name and (on error) the exception
class — never tool arguments, cantons or surveillance data.
Available Disease Topics
Category | Topics |
Respiratory | influenza, covid19, acute_respiratory_infection, respiratory_pathogens |
Enteric | campylobacteriosis, salmonellosis, ehec, listeriosis, hepatitis_a/e |
STI & Bloodborne | hiv, aids, syphilis, gonorrhea, hepatitis_b/c, chlamydiosis |
Vaccine-preventable | measles, pertussis, rubella, tetanus, diphtheria, ipd, meningo |
Vector-borne | lyme_borreliosis, tick-borne_encephalitis, dengue, malaria, zika |
Wastewater | wastewater_viral_load, wastewater_sequencing |
Demo
Claude asking about the influenza situation in canton Zurich — single tool call, structured result, actionable German-language summary.
MCP Protocol Version
This server speaks MCP 2026-07-28 natively, and still serves every older
client over the same endpoint. The client's first request on a connection
decides the era; a later claim from the other era is refused.
Era | Revision | Who reaches it |
Per-request envelope |
| A request carrying the |
|
| Clients that do not speak |
What "natively" means here, each point asserted in
tests/test_spec_2026_07_28.py:
No session, in either era. No response carries
Mcp-Session-Id; any replica can answer any request, so a plain round-robin load balancer is enough (see deployment & scaling). For handshake clients this is a deliberatestateless_http=True.No deprecated capabilities. Protocol logging (
ctx.info/ctx.warning), sampling and roots are deprecated in2026-07-28(SEP-2577). The server uses none of them; operational logs go to stderr. The test suite turnsMCPDeprecationWarninginto an error, so a reintroduced call fails CI.No server-to-client requests. No tool asks the client anything, so nothing depends on a back-channel
2026-07-28no longer has.Progress (server-to-client, still in the spec) arrives in both eras, on the response stream of the tool call.
Cache hints (
ttlMs/cacheScope, SEP-2549) on the listing methods, and CORS for the routing headersMcp-Method,Mcp-Name,Mcp-Protocol-Version.
Both revisions are pinned in
tests/test_protocol_version.py and asserted
against the installed SDK, so a Dependabot bump of mcp cannot move either one
silently. The handshake ceiling is measured against a live initialize through
the assembled ASGI stack, not read off a constant name.
Note that the SDK's LATEST_PROTOCOL_VERSION is an alias for the modern
era, not for the handshake era — pinning against it alone would leave the
handshake era free to drift.
Update policy. When the gate fails, do not edit the constant blindly: read
the spec changelog between the two revisions, verify the server still behaves,
then move the constant, this section, README.de.md and
CHANGELOG.md together.
Safety & Limits
Aspect | Details |
Access | Read-only — no write operations possible |
Egress | Code-layer allow-list: the server only contacts three public data hosts ( |
Personal data | None — all sources are aggregated/anonymised (BAG IDD at canton level by law; indicators are population aggregates by age/sex/region) |
Rate limits | No published IDD API rate limit; server caps responses at 104 data points per call by default ( |
Timeout | 30 s per API call |
Authentication | No API keys required — all data publicly accessible |
Data licence | opendata.swiss OGD — free use, source attribution required (CC BY-equivalent). FOPH IDD must be cited; see Data sources & licences |
Terms of Service | Subject to BAG IDD API ToS |
Known Limitations
Beta API: IDD API is labelled
v0.1 beta— schema may change without noticeWeekly cadence: Data is not real-time; updated Wednesdays only
Canton granularity: Some rare diseases have insufficient cases for canton-level data (suppressed for privacy)
Age groups: Available dimensions vary by disease series; use
bag_health_mcp__get_series_detailsto check
Compliance
ISDS (Stadt Zürich): a draft information-security protection-needs classification (Schutzbedarfsanalyse per Grundwert + measures mapping) is in
docs/isds-klassifikation.md. It is a technically-grounded draft pending ISBO/OIZ sign-off — not a binding classification.Data classification (Schulamt): the data is classified ÖFFENTLICH / BUI (public OGD, no personal data, aggregated at canton level with small cells suppressed at source). Draft scheme + aggregation-risk note in
docs/datenklassifikation-schulamt.md; the aggregatingbag_health_mcp__get_canton_situationtool surfaces this in its response.Security posture: lethal-trifecta assessment (the server is strictly read-only → not affected), secret-management decision (no secrets — public data), and network-exposure notes are in
docs/security-posture.md.Phase architecture: this is a Phase 1 (read-only) server; write/send capabilities are deferred behind documented prerequisites. See
docs/roadmap.md.Reporting vulnerabilities: see the security policy for how to report security issues privately.
Contributing
See CONTRIBUTING.md (Deutsch).
Security
See SECURITY.md (Deutsch) for the security posture and how to report a vulnerability confidentially.
License
Code: MIT (see LICENSE).
Data: BAG IDD is Open Government Data on opendata.swiss under free use with mandatory source attribution (Swiss OGD terms, CC BY-equivalent) — not public domain. Cite the Federal Office of Public Health FOPH (IDD) when reusing the data; see Data sources & licences.
Author
Hayal Oezkan · github.com/malkreide
Related Portfolio Servers
swiss-statistics-mcp— BFS demographic databag-epl-mcp— BAG medication reimbursement listzurich-opendata-mcp— City of Zurich open data
Installation
Run via uv's uvx — no clone or manual install needed. Add to your MCP client config (mcpServers for Claude Desktop, Cursor and Windsurf; use a top-level servers key for VS Code in .vscode/mcp.json):
{
"mcpServers": {
"bag-health-mcp": {
"command": "uvx",
"args": [
"bag-health-mcp"
]
}
}
}Available Tools
10 toolsbag_health_mcp__download_exportARead-onlyIdempotent
Download a complete export dataset from the BAG IDD as CSV or JSON. Returns the raw data content for a specific disease file. Useful for bulk analysis. Files are updated weekly.<use_case>Retrieve a full raw dataset (all rows) for one disease for downstream/offline analysis.</use_case><important_notes>The preview is truncated at 3000 chars; for very large datasets use the IDD web interface. Get file names from bag_health_mcp__list_export_files.</important_notes>bag_health_mcp__download_export(file='INFLUENZA_oblig', format='csv') -> raw CSV content.
Inputs: params (required). Returns: file, note, rows, format, +3 more
bag_health_mcp__get_canton_situationARead-onlyIdempotent
Get a public health situation overview for a specific canton or Switzerland. Combines current incidence data for key school-relevant diseases (influenza, measles, norovirus proxy via acute_respiratory_infection) with trend information. Designed for school authorities and city administration Public Health Reporting. <use_case>One-call situational overview for a canton (Schulamt / city administration) without orchestrating multiple series queries.</use_case><important_notes>Aggregates several series; a single unavailable series is reported as a per-disease status, not a failure of the whole call.</important_notes>bag_health_mcp__get_canton_situation(canton='ZH') -> per-disease latest value, trend and change for Zurich. Anchor query: 'Wie ist die aktuelle Grippesituation im Kanton Zürich?'
Inputs: canton, include_wastewater. Returns: note, canton, diseases, provenance, +1 more
bag_health_mcp__get_data_versionARead-onlyIdempotent
Get the current data version of the BAG IDD. Returns the date of the last data update (format YYYYMMDD). IDD is updated every Wednesday.<use_case>Check how fresh the data is / which weekly snapshot you are looking at.</use_case><important_notes>Data is updated only weekly (Wednesdays); not real-time.</important_notes>bag_health_mcp__get_data_version() -> version='20260325', date='2026-03-25'.
Inputs: params (required). Returns: date, note, version, provenance
bag_health_mcp__get_disease_dataARead-onlyIdempotent
Fetch time-series surveillance data for a disease from the BAG IDD. Returns weekly or yearly case counts, incidence rates, or other metrics. Data updated every Wednesday. <use_case>Get the actual numbers/trend for a disease in a canton over time — the core data-retrieval tool.</use_case><important_notes>Call bag_health_mcp__get_series_details first for valid filters. 'incValue' = incidence per 100'000; 'value' = absolute count.</important_notes>bag_health_mcp__get_disease_data(series_id='influenza/cases/incValue/iso_week', canton='ZH') -> weekly influenza incidence for Zurich.
Inputs: params (required). Returns: topic, results, summary, series_id, +5 more
bag_health_mcp__get_indicator_seriesARead-onlyIdempotent
Fetch one health indicator's time series from Obsan, the Versorgungsatlas or Sucht Schweiz (HBSC). Use an indicator_id from bag_health_mcp__search_health_indicators. Obsan publishes an indicator in several CUTS (national, by canton, by age class, by social position, as a distribution); this tool picks one, names it in 'variant' and lists the others in 'variants_available'. They are different measurements with different units, not interchangeable. Pass region='ZH' for the cantonal cut where the indicator has one. Versorgungsatlas returns a cantonal year/value series (26 cantons + a 'CH' total, 95% CIs, canton-vs-Switzerland ratio). IMPORTANT: AGGREGATED population statistics only — NOT individual advice, diagnosis or case assessment, no personal data. For 'suchtschweiz' (school-context prevention topics) the values are national HBSC survey aggregates by age/sex. <use_case>Get a national trend, or a cantonal series with a Switzerland comparison.</use_case><important_notes>Read 'variant' before reading the numbers: 'g'/'kg' are rates, 'gum' is a distribution in %. The HBSC youth series (source='suchtschweiz', ages 11-15) is national only — a canton request returns the national cut with a note, because HBSC is not cantonally representative. Some Obsan observations are pooled spans ('1998-02' = 1998–2002); those carry the full label in 'period' and its first year in 'year'. Where an indicator publishes no series, the call fails with that reason instead of returning an empty series.</important_notes>bag_health_mcp__get_indicator_series(source='obsan', indicator_id='obsan/lebenserwartung', region='ZH') -> ZH life expectancy from the 'kg' cut, with the source's own canton and category legends.
Inputs: params (required). Returns: note, unit, title, points, +12 more
bag_health_mcp__get_series_detailsARead-onlyIdempotent
Get metadata and available filter values for a specific data series. Shows which canton, age group, sex, and other dimensions are available. Always call this before bag_health_mcp__get_disease_data to know valid filter options.<use_case>Learn the valid filter values (cantons, age groups, sex) for a series so a subsequent data query uses accepted parameters.</use_case><important_notes>Available dimensions vary by series — always check here rather than assuming.</important_notes>bag_health_mcp__get_series_details(series_id='influenza/cases/incValue/iso_week') -> cantons=['ZH','BE',...], age_groups=[...].
Inputs: params (required). Returns: note, cantons, series_id, age_groups, +3 more
bag_health_mcp__list_diseasesARead-onlyIdempotent
List all 51 disease topics available in the BAG Infectious Disease Dashboard (IDD). Returns the topic slug needed for other tools, grouped by category (respiratory, enteric, STI, vector-borne, wastewater). <use_case>Discover what diseases are available before querying data.</use_case><important_notes>Start here; the topic slugs returned are required inputs for the other tools.</important_notes>bag_health_mcp__list_diseases() -> categories incl. 'influenza', 'measles', 'covid19'.
Inputs: params (required). Returns: usage, categories, provenance, total_topics
bag_health_mcp__list_export_filesARead-onlyIdempotent
List all available export file names from the BAG IDD. These are complete datasets (CSV/JSON) per disease, e.g. INFLUENZA_oblig, COVID19_wastewater_sequencing, MEASLES_oblig. Use with bag_health_mcp__download_export to get raw data files.<use_case>Discover which complete bulk datasets can be downloaded for offline/bulk analysis.</use_case><important_notes>Returns file names, not the data — pass one to bag_health_mcp__download_export.</important_notes>bag_health_mcp__list_export_files() -> ['INFLUENZA_oblig', 'COVID19_wastewater_sequencing', ...].
Inputs: params (required). Returns: files, usage, version, provenance, +1 more
bag_health_mcp__list_seriesARead-onlyIdempotent
List all available data series for a specific disease topic. Each series is identified by 'topic/chapter/aggregation/temporality'. Returns series IDs to use with bag_health_mcp__get_series_details and bag_health_mcp__get_disease_data.<use_case>Find which exact series exist for a disease (e.g. weekly cases vs yearly incidence) before fetching data.</use_case><important_notes>Needs a valid topic slug from bag_health_mcp__list_diseases.</important_notes>bag_health_mcp__list_series(topic='influenza') -> 'influenza/cases/incValue/iso_week', ...
Inputs: params (required). Returns: topic, usage, chapters, provenance, +2 more
bag_health_mcp__search_health_indicatorsARead-onlyIdempotent
Search health indicators across three Swiss sources: 'obsan' (Swiss Health Observatory — hundreds of indicators incl. the HBSC youth-survey series), 'versorgungsatlas' (Swiss health-care supply atlas, ~124 indicators), and 'suchtschweiz' (addiction / HBSC series, served via Obsan's official mirror). Returns matching indicator_ids to pass to bag_health_mcp__get_indicator_series. IMPORTANT: this serves AGGREGATED population statistics (prevalences/metrics by age/sex/region) — NOT individual advice, diagnosis or case assessment, and no personal data. Especially for 'suchtschweiz' (prevention topics in a school context): the figures are population-level survey aggregates only. <use_case>Find which indicators exist for a topic (e.g. youth alcohol) before fetching a series.</use_case><important_notes>The catalogue does not state which cuts an indicator publishes — get_indicator_series reports that per indicator ('variant', 'variants_available'). Most Obsan indicators DO have a cantonal cut (50 of 60 sampled); the HBSC youth series (source='suchtschweiz', ages 11-15) is the exception and is national only, as HBSC is not cantonally representative. Other 'monam' indicators come from the Swiss Health Survey and are cantonal. A few catalogue entries have no series at all; the series call names that case rather than returning nothing.</important_notes>bag_health_mcp__search_health_indicators(source='suchtschweiz', topic='alkohol') -> Obsan HBSC alcohol-prevalence indicators.
Inputs: params (required). Returns: query, usage, source, indicators, +3 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
The tools are mostly distinct, but the term 'series' appears in list_series, get_series_details, and get_indicator_series, which could cause slight confusion. Descriptions clearly differentiate sources (BAG IDD vs Obsan/other indicators), so an attentive agent can tell them apart.
All tool names follow a consistent snake_case verb_noun pattern with the same prefix, e.g. list_diseases, get_disease_data, download_export. No deviations or mixed conventions.
10 tools is well within the ideal range for a data-access server; each tool serves a clear purpose in discovery, metadata, or retrieval, with no obvious redundancy.
The surface covers full workflows for both disease surveillance (list -> series -> details -> data) and indicators (search -> fetch), plus bulk export and versioning. A minor gap is the lack of a dedicated 'list all indicators' tool, but search likely covers this.
Maintenance
Related MCP Connectors
opendata.swiss MCP — Switzerland's federal open-data portal (CKAN catalogue).
WHO GHO MCP — World Health Organization Global Health Observatory (free, no auth)
MCP gateway federating 26 biomedical MCP servers behind one endpoint: gnomAD, ClinVar, HPO, VEP.
MCP server for US nursing facility search and ownership lookup (NursingHomeDatabase).
Related MCP Servers
- AlicenseAqualityBmaintenanceMCP server connecting AI models to Swiss Federal Food Safety and Veterinary Office open data, enabling queries about food recalls, animal disease surveillance, food control results, and more.1134 PyPIMIT
- AlicenseAqualityBmaintenanceMCP server for Swiss federal geodata -- maps, elevation, geocoding, cadastral extracts, and downloadable datasets via Swisstopo APIs.2039 PyPI12MIT
- AlicenseAqualityAmaintenanceMCP Server for Swiss road mobility — shared vehicles, EV charging, traffic alerts, Park & Rail, and multimodal trip planning.1538 PyPI1MIT
- AlicenseAqualityBmaintenanceMCP server for Swiss federal legislation metadata via Fedlex, enabling search and retrieval of act details with ELI URIs, SR numbers, and multilingual support.346 PyPIApache 2.0