bag-health-mcp

bag-health-mcp

MCP server for the Swiss Federal Office of Public Health Infectious Disease Dashboard, providing access to epidemiological surveillance data for 51 pathogens across Switzerland, including influenza, COVID-19, measles, and wastewater surveillance.

Category
Visit Server

README

πŸ₯ bag-health-mcp

PyPI Python 3.11+ License: MIT Swiss Public Data MCP Portfolio

Part of the Swiss Public Data MCP Portfolio β€” connecting AI models to Swiss public data sources.

πŸ‡©πŸ‡ͺ Deutsche Version

MCP server for the Swiss Federal Office of Public Health (BAG) Infectious Disease Dashboard (IDD). Access epidemiological surveillance data for 51 pathogens across Switzerland β€” including influenza, COVID-19, measles, wastewater surveillance, and more.


🎯 What You Can Do

"Wie ist die aktuelle Grippesituation im Kanton ZΓΌrich verglichen mit den letzten Wochen?"
β†’ bag_health_mcp__get_canton_situation(canton="ZH")

"Gibt es aktuell einen Masernausbruch in der Schweiz?"
β†’ bag_health_mcp__get_disease_data(series_id="measles/cases/incValue/year", canton="all")

"Wie entwickelt sich das SARS-CoV-2-Signal im Abwasser?"
β†’ bag_health_mcp__list_series(topic="wastewater_viral_load")
β†’ bag_health_mcp__get_disease_data(series_id="wastewater_viral_load/NA/value/date", ...)

"Welche Krankheitsdaten stellt das BAG aktuell bereit?"
β†’ bag_health_mcp__list_diseases()
β†’ More use cases by audience β†’

πŸ”§ Tools

Tool Description
bag_health_mcp__list_diseases List all 51 disease topics, grouped by category
bag_health_mcp__list_series List data series for a specific disease
bag_health_mcp__get_series_details Get available filter dimensions (canton, age, sex)
bag_health_mcp__get_disease_data Fetch time-series surveillance data
bag_health_mcp__get_canton_situation Situational overview for a canton (Schulamt use case)
bag_health_mcp__list_export_files List available complete export datasets
bag_health_mcp__download_export Download raw CSV/JSON export
bag_health_mcp__get_data_version Current data version (updated every Wednesday)

Tool annotations

All tools carry MCP tool annotations so a host can reason about them without calling. Every tool is identical here β€” it only ever reads from the public BAG IDD API:

Annotation Value Meaning
readOnlyHint true No tool mutates any state.
destructiveHint false No destructive side effects.
idempotentHint true Repeating a call has no additional effect.
openWorldHint true Tools reach an external system (the IDD API).

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 8 tools.

🧩 MCP Primitives

This server uses all three MCP primitives, each for what it is best at:

Tools (8) β€” live, parameterised actions that call the IDD API (above).

Resources β€” static, read-only reference data a host can fetch and cache, no arguments or upstream call needed:

Resource URI Description
bag://reference/cantons Canton codes accepted by the tools (incl. FL, all)
bag://reference/disease-categories Disease-topic taxonomy by category
bag://reference/data-licence Source, attribution and licence terms

Prompts β€” reusable, parameterised workflows a host can surface (e.g. as slash-commands):

Prompt Arguments Purpose
canton_situation_brief canton Draft a Schulamt public-health situation brief
outbreak_check disease, canton 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 / KreisschulbehΓΆrden:

  • Monitor influenza and ARI incidence in your canton
  • Single measles case β†’ alert for schools with low vaccination coverage
  • Pertussis tracking β†’ 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 β†’ "What treatments are listed?" (EPL medication database)
  • bag-health-mcp β†’ "What is currently spreading?" (surveillance data)

πŸ“‘ Data Source

  • IDD API: https://api.idd.bag.admin.ch β€” No authentication required
  • Update 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 β€” free use, source attribution required (Swiss OGD terms, CC BY-equivalent) Yes

Required citation: Federal Office of Public Health FOPH β€” Infectious Disease Dashboard (IDD), open data via opendata.swiss. Every tool response carries this in a provenance block (attribution + license fields) so downstream consumers can surface it automatically.

Architecture:
                    β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
  MCP Host          β”‚  bag-health-mcp β”‚
  (Claude, etc.) ──▢│  MCP SDK        │──▢ api.idd.bag.admin.ch
                    β”‚  8 Tools        β”‚    (IDD API, no auth)
                    β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

πŸš€ 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 8000

Transport, host and port are set via environment variables β€” MCP_TRANSPORT (http/stdio), MCP_HOST, MCP_PORT β€” 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 β€” the provided Dockerfile does this.

⚠️ Security: HTTP transport exposes the server on the network. Only bind beyond 127.0.0.1 in a network-isolated environment β€” 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. See docs/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 Mcp-Session-Id header is exposed so stateful sessions work. Empty = no cross-origin (never a wildcard).

For running at scale (session affinity, 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 β€” 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-mcp

Tracing 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 β€” never tool arguments, cantons or surveillance data.


πŸ—‚οΈ 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

πŸ–ΌοΈ Demo

Demo: Claude queries BAG IDD via bag-health-mcp

Claude asking about the influenza situation in canton Zurich β€” single tool call, structured result, actionable German-language summary.


πŸ”’ Safety & Limits

Aspect Details
Access Read-only β€” no write operations possible
Egress Code-layer allow-list: the server only contacts the BAG IDD API, HTTPS-only, enforced on every request incl. redirect hops (SSRF/SEC-004 + SEC-021). Network-layer companion policy in deploy/networkpolicy.yaml
Personal data None β€” BAG IDD data is aggregated and anonymised at canton level by law
Rate limits No published IDD API rate limit; server caps responses at 104 data points per call by default (limit_weeks param)
Timeout 30 s per API call
Authentication No API keys required β€” all data publicly accessible
Data licence opendata.swiss OGD β€” 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 β€” schema may change without notice
  • Weekly 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_details to check

πŸ‡¨πŸ‡­ Compliance

  • ISDS (Stadt ZΓΌrich): 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 β€” not a binding classification.
  • Data classification (Schulamt): the data is classified Γ–FFENTLICH / 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 aggregating bag_health_mcp__get_canton_situation tool surfaces this in its response.
  • Security posture: lethal-trifecta assessment (the server is strictly read-only β†’ not affected), secret-management decision (no secrets β€” 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.

πŸ“„ 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) β€” not public domain. Cite the Federal Office of Public Health FOPH (IDD) when reusing the data; see Data sources & licences.

πŸ”— Related Portfolio Servers

<!-- mcp-name: io.github.malkreide/bag-health-mcp -->

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured