mcpField
K
Kolada MCP Server

Kolada MCP Server

Local
github.com/aerugoLegal & Government16Updated 48w ago

About Kolada MCP Server

Kolada MCP Server gives AI applications access to Sweden’s Kolada municipal and regional statistics API. It offers KPI search, metadata and data retrieval, plus comparison and filtering tools for public-sector analysis.

Key features

  1. 01Nine tools for Kolada data
  2. 02Semantic KPI search
  3. 03KPI metadata and data retrieval
  4. 04Municipality and region comparisons
  5. 05Filter municipalities by KPI thresholds

Use cases

  1. 01Finding KPIs with natural-language queries
  2. 02Comparing municipal KPI results
  3. 03Filtering municipalities by indicator thresholds

MCP support

The MCP server exposes nine tools for searching Kolada indicators, retrieving data, and analyzing municipalities and regions. It supports stdio and HTTP transport modes.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Kolada MCP Server

A clean, standalone MCP (Model Context Protocol) server for Sweden's Kolada municipal statistics API.

Overview

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.

Features

  • 9 MCP Tools for comprehensive data access
  • Semantic Search using Swedish BERT embeddings
  • No External Dependencies - fully standalone (no Mima or Redis)
  • Containerized with Docker support
  • Modern Python 3.11+ with type hints and async/await

Available Tools

ToolDescription
list_operating_areasList all KPI categories with counts
get_kpis_by_operating_areaGet KPIs within a specific category
search_kpisSemantic search for KPIs using natural language
get_kpi_metadataGet detailed metadata for a specific KPI
fetch_kolada_dataFetch raw KPI data for municipalities
analyze_kpi_across_municipalitiesComparative analysis with rankings
compare_kpisCompare two KPIs (difference or correlation)
list_municipalitiesList municipalities/regions
filter_municipalities_by_kpiFilter by KPI threshold

Installation

Using pip
pip install -e .
Using Docker
docker-compose up -d kolada-mcp

Usage

Stdio Mode (Default)
kolada-mcp
# or
python -m kolada_mcp
HTTP Mode
MCP_TRANSPORT=http PORT=8001 kolada-mcp
Claude Desktop Integration

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "kolada": {
      "command": "kolada-mcp"
    }
  }
}

Configuration

Environment variables:

VariableDefaultDescription
MCP_TRANSPORTstdioTransport mode (stdio or http)
PORT8001HTTP server port
LOG_LEVELINFOLogging level

Development

Setup
# Create virtual environment
python -m venv .venv
source .venv/bin/activate

# Install with dev dependencies
pip install -e ".[dev]"
Running Tests
pytest
Code Quality
# Linting
ruff check src tests

# Type checking
mypy src

Architecture

src/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 tools

License

Apache-2.0

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.