🇨🇭 Part of the Swiss Public Data MCP Portfolio

SECO Labor Market MCP Server

🌐 English | Deutsch

An MCP (Model Context Protocol) server for Swiss labor market data from SECO (Staatssekretariat für Wirtschaft) and AMSTAT via opendata.swiss.

Overview

This server connects AI models to Swiss labor market statistics — unemployment rates, job seekers, open positions, youth unemployment, and occupational breakdowns — all without requiring an API key.

Primary audiences:

• 🏫 Schulamt / Education planning — youth unemployment, vocational guidance data
• 📊 Research & analysis — labor market trends, cantonal comparisons
• 🤖 AI agents — automated labor market monitoring and reporting

Anchor query:
"Welche Berufsgruppen haben im Kanton Zürich die höchste Jugendarbeitslosigkeit, und welche Lehrberufe unterliegen der Stellenmeldepflicht?" → More use cases by audience →

Data Sources (Phase 1 — No Auth Required)

Architecture

┌─────────────────────────────────────────────────────┐
│                  seco-labor-mcp                     │
│                                                     │
│  ┌─────────────┐    ┌──────────────────────────┐   │
│  │  FastMCP    │    │      9 MCP Tools         │   │
│  │  Server     │◄──►│  seco_search_datasets    │   │
│  │  (stdio /   │    │  seco_get_dataset        │   │
│  │   HTTP)     │    │  seco_get_unemployment_* │   │
│  └─────────────┘    │  seco_get_youth_*        │   │
│         │           │  seco_get_job_seekers    │   │
│         ▼           │  seco_get_open_positions │   │
│  ┌─────────────┐    │  seco_get_monthly_url    │   │
│  │  httpx      │    │  seco_list_cantons       │   │
│  │  async      │    └──────────────────────────┘   │
│  └──────┬──────┘                                   │
└─────────┼───────────────────────────────────────────┘
          │
          ▼
  ┌───────────────────────────────────┐
  │  opendata.swiss CKAN API          │
  │  https://opendata.swiss/api/3/    │
  │  action/package_search            │
  │  action/package_show              │
  └───────────┬───────────────────────┘
              │
              ▼
  ┌───────────────────────────────────┐
  │  SECO Data Resources              │
  │  CSV / XLSX / PDF Downloads       │
  │  (monthly labor market data)      │
  └───────────────────────────────────┘

Where the figures come from — and what is missing

SECO is no longer a publisher on opendata.swiss. Verified 2026-08-14: organization_show returns 404, and none of the 176 entries in organization_list is SECO. Until then the server filtered every search on that organisation and therefore returned nothing — a name lookup that misses looks exactly like an empty search.

The registered unemployed and job seekers are still SECO's figures: the BFS publishes them in table T3.3.0.1 and names SECO in the footer. The server reads that table through a pinned dataset id (sources.py), checked against the live source by a live test.

thousands, annual average

The three series do not measure the same thing: in 2000 the ILO figure is 1.76× the registered one. The server reports them separately and labelled, and never converts one into the other.

The cantonal layer: four cantons, four schemas

There is no national monthly series — but four cantons publish their own RAV figures, each in its own portal with its own column names. For those, seco_get_unemployment_overview(canton=…) returns real values:

The other 22 cantons get a named refusal — no figure from another canton and no national aggregate. Partial coverage that feels complete is worse than none.

The four series are not comparable with each other and do not add up to a Swiss figure: different time axes, different geographic levels, and in ZG's case a rate rather than a count.

Still not available: unemployment by occupational group, open positions as a national series, and youth unemployment for Switzerland or for 24 of the 26 cantons. The affected tools say so and return no substitute figure. These values exist interactively on amstat.ch, which offers no interface a server could call.

Tools

12 of a maximum of 15 tools.

Unfallstatistik UVG (SSUV)

The three seco_get_uvg_* tools cover the risk side of the same labour market the unemployment tools describe: how many occupational accidents and diseases occur per branch, and how that develops over ten years.

The publisher is not SECO. The Unfallstatistik UVG is issued by the Koordinationsgruppe KSUV and the Sammelstelle SSUV c/o Suva, Lucerne. The seco_ prefix addresses this server, not the source; every response names the actual publisher in its source field.

Architecture decision: C (dump-first)

Verified live on 2026-08-05, full write-up in PROBE_REPORT_UVG.md.

The source has no API. A link scan across every data page returned 165 PDFs and zero files with .csv, .xlsx or .json. opendata.swiss does not list the source at all (count=0 for six of seven search terms), and the BFS dam-api silently ignores its filter parameters. What remains is machine-readable in practice but not by design:

PDFs are cached for 24 h and fetched with 2s/4s/8s backoff.

What every response tells you

• source_freshness.data_year — the data year, not the edition year. The 2026 edition reports 2024; that two-year lag is stated, not buried.
• totals_check — parsed rows are summed and compared against the total printed in the same publication. A broken layout shows up here instead of becoming a plausible wrong number.
• significant — the source marks statistically significant year-on-year changes with an asterisk. That flag is preserved per data point, so a change is only reported as significant where the source says so.

Installation

Claude Desktop (stdio)

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "seco-labor": {
      "command": "uvx",
      "args": ["seco-labor-mcp"]
    }
  }
}

Cloud / HTTP

pip install seco-labor-mcp
MCP_TRANSPORT=http PORT=8000 seco-labor-mcp

http is the transport to use. It is the only one that can carry the modern protocol era: measured against this server object, http negotiates 2026-07-28 while sse caps every client at 2025-11-25, even a client that offers the modern era. sse and streamable-http remain accepted for existing deployments — tests/test_transport_aera.py runs both and records which era each one actually yields.

The HTTP server binds to 127.0.0.1 (loopback) by default to prevent NeighborJack on shared networks. For container deployments where you actually need to accept traffic from outside the container, set HOST=0.0.0.0 explicitly — ideally in your Dockerfile / orchestrator config, and only behind an upstream proxy or firewall:

HOST=0.0.0.0 MCP_TRANSPORT=http PORT=8000 seco-labor-mcp   # container only

An unknown MCP_TRANSPORT value now exits with an error. It used to fall back to stdio silently, so a typo produced a server that simply never appeared on the expected port.

Development

git clone https://github.com/malkreide/seco-labor-mcp.git
cd seco-labor-mcp
pip install -e ".[dev]"
pytest tests/ -m "not live" -v

Usage Examples

Search for youth unemployment data

Tool: seco_search_datasets
Input: { "query": "Jugendarbeitslosigkeit Alter", "limit": 5 }

Get cantonal unemployment for Zürich

Tool: seco_get_unemployment_overview
Input: { "canton": "ZH", "response_format": "markdown" }

Get monthly report URL

Tool: seco_get_monthly_report_url
Input: { "year": 2026, "month": 2, "language": "de" }

Key Concepts

Arbeitslose vs. Stellensuchende

Eselsbrücke: Arbeitslose ⊂ Stellensuchende — Arbeitslose sind eine Teilmenge.

Youth Unemployment Seasonality

• July/August: Sharp increase (school leavers without placements)
• September/October: Decline (apprenticeship starts)
• The residual that remains after the autumn decline signals structural need for bridge programs (Brückenangebote)

Stellenmeldepflicht (since 2020)

Occupations with ≥5% unemployment rate must be reported to the RAV before posting publicly. The list changes annually. This is directly relevant for vocational counseling — these professions have highest availability for Swiss job seekers.

Portfolio Synergies

Known Limitations

• amstat.arbeit.swiss has no public REST API (JavaScript SPA) → workaround via CKAN
• Occupational/sectoral detail requires CSV download from SECO resources
• Monthly press report URL patterns may vary for older reports
• Cantonal sub-municipal data not available at this level
• UVG figures come from PDF parsing — the layout was stable across the 2025 and 2026 editions, but a redesign can break it. The totals_check in every response is what makes such a break visible rather than silent.
• UVG data lags roughly two years (the 2026 edition reports 2024)
• UVG branch detail follows NOGA 2008 and groups some divisions (41 – 42, 77, 79 – 82); there is no cantonal breakdown at this level
• Detailed UVG data beyond the publications sits behind the SSUV closed user group and is out of scope for this no-auth server

Phase 2 roadmap:

• Automatic CSV caching with 24h TTL
• Direct XLSX parsing for cantonal breakdowns
• Integration with zh-education-mcp for Schulamt-specific correlations

Data License

Two different licences apply — the code of this server is MIT either way, but the data is not covered by it.

SECO / AMSTAT data published on opendata.swiss is under Creative Commons CCZero (public domain). Source: Staatssekretariat für Wirtschaft (SECO) — seco.admin.ch

Unfallstatistik UVG data is not openly licensed. The publication states:

«Abdruck – ausser für kommerzielle Nutzung – mit Quellenangabe gestattet.» (Reproduction permitted, except for commercial use, with attribution.)

That is a non-commercial restriction with an attribution requirement. It belongs to KSUV/SSUV and cannot be lifted by this repository's MIT licence: the MIT terms cover the code, not the figures the code retrieves. If you use this server commercially, the UVG tools are not covered — clarify directly with the Sammelstelle (unfallstatistik@suva.ch). Every UVG response repeats this restriction in its source field, because a README is not passed to the model.

Safety & Limits

MCP Protocol Version

This server serves two protocol eras over the same server object, on fastmcp 4.x / mcp 2.x:

A client that offers the modern era gets it; a client that only knows the handshake era still gets served. Both are pinned separately in tests/test_protokoll_aeren.py, and both are measured — the test negotiates a real connection against this server object rather than comparing two constants.

Pinning only LATEST_PROTOCOL_VERSION would not be enough: in mcp 2.x that name is an alias for the modern era, so it would leave the handshake ceiling free to move — and that ceiling is what most clients in the field actually speak.

Until 0.4.0 this server ran fastmcp 3.x, which pins mcp 1.x. There 2025-11-25 is the highest revision the SDK knows at all, so 2026-07-28 was not partially supported — it was absent. The test that used to guard the one-era state now guards its opposite: it fails if a downgrade takes the modern era away again.

Note for anything reading server metadata: on a modern connection there is no InitializeResult. Use the era-neutral protocol_version / server_info instead of initialize_result.

Contributing

See CONTRIBUTING.md for development guidelines.

Security

See SECURITY.md for the security posture and how to report a vulnerability.

License

Released under the MIT License — Copyright © 2026 Hayal Oezkan.

Author

Hayal Oezkan · github.com/malkreide

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": {
    "seco-labor-mcp": {
      "command": "uvx",
      "args": [
        "seco-labor-mcp"
      ]
    }
  }
}