Kolada Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Kolada Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A clean, standalone MCP (Model Context Protocol) server for Sweden's Kolada municipal statistics API.
This server provides AI applications with access to Sweden's comprehensive municipal and regional statistics database. It enables natural language queries against thousands of Key Performance Indicators (KPIs) covering various aspects of Swedish public sector data.
| Tool | Description |
|---|---|
list_operating_areas | List all KPI categories with counts |
get_kpis_by_operating_area | Get KPIs within a specific category |
search_kpis | Semantic search for KPIs using natural language |
get_kpi_metadata | Get detailed metadata for a specific KPI |
fetch_kolada_data | Fetch raw KPI data for municipalities |
analyze_kpi_across_municipalities | Comparative analysis with rankings |
compare_kpis | Compare two KPIs (difference or correlation) |
list_municipalities | List municipalities/regions |
filter_municipalities_by_kpi | Filter by KPI threshold |
pip install -e .docker-compose up -d kolada-mcpkolada-mcp
# or
python -m kolada_mcpMCP_TRANSPORT=http PORT=8001 kolada-mcpAdd to your Claude Desktop configuration:
{
"mcpServers": {
"kolada": {
"command": "kolada-mcp"
}
}
}Environment variables:
| Variable | Default | Description |
|---|---|---|
MCP_TRANSPORT | stdio | Transport mode (stdio or http) |
PORT | 8001 | HTTP server port |
LOG_LEVEL | INFO | Logging level |
# Create virtual environment
python -m venv .venv
source .venv/bin/activate
# Install with dev dependencies
pip install -e ".[dev]"pytest# Linting
ruff check src tests
# Type checking
mypy srcsrc/kolada_mcp/
├── __init__.py # Package init
├── __main__.py # Entry point
├── config.py # Settings (Pydantic)
├── server.py # FastMCP server
├── models/
│ └── types.py # Data models
├── services/
│ ├── kolada_client.py # API client
│ ├── embeddings.py # Semantic search
│ └── data_processing.py
└── tools/
├── metadata.py # KPI metadata tools
├── data.py # Data fetching tools
├── municipality.py # Municipality tools
└── comparison.py # Comparison toolsApache-2.0
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.