Kolada

Provides access to 5,000+ KPIs across 264 operating areas for all Swedish municipalities and regions via MCP-compatible endpoints.
  • javascript

8

GitHub Stars

javascript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

Kolada MCP Server connects LLMs and AI chatbots to 5,000+ KPIs across 264 operating areas for all Swedish municipalities and regions. You can access data directly via a remote URL or run the server locally to integrate with your AI clients and workflows.

How to use

You connect your MCP client to the Kolada MCP Server using either the remote MCP URL or a local runtime. The remote endpoint exposes a standard MCP interface you can call from your AI assistant to fetch KPI metadata, perform searches, filter data, and run analyses. For local use, you run a local MCP server process and point your client to the local process over standard MCP transports.

How to install

Prerequisites you need before you start:

  • Node.js and npm installed on your machine.

  • Internet access to install dependencies (for local setup).

How to install

# 1) Run the MCP server remotely (no local install required)
# You can connect your clients to this URL:
# https://kolada-mcp-pafn.onrender.com/mcp

To run the MCP server locally using the quickest method, you use the npx command shown below.

npx kolada-mcp-server

If you prefer a global installation, install the package globally and start the server with the provided command.

npm install -g kolada-mcp-server
kolada-mcp-server

Configuration and usage notes

You can connect popular AI clients using their MCP connection options. When using a remote server, point your client at the remote URL below. For local usage with npx, simply run the command and connect to the local process.

Endpoints and transport

The MCP server exposes multiple endpoints to support different communication styles. Use HTTP for standard MCP interactions or Server-Sent Events (SSE) for streaming updates from the server. The health endpoint lets you verify the server status.

Security and best practices

Keep the server updated and run it behind standard security measures. Use environment variables for secrets, enable rate limiting and timeouts, and monitor for vulnerabilities with automated security tooling as described in the security guidelines.

Notes

A remote MCP URL is available for quick integration. Local usage via npx provides a zero-setup path for experimentation and development. Ensure you only point clients to MCP endpoints you trust and verify data usage and attribution when presenting Kolada data in a service.

Available tools

search_kpis

Fritextsökning bland 5 000+ nyckeltal

get_kpi

Hämta metadata för ett nyckeltal via ID

get_kpis

Hämta flera nyckeltal samtidigt (max 25)

get_kpi_groups

Lista tematiska grupper

get_kpi_group

Hämta alla nyckeltal i en grupp

list_operating_areas

Lista 264 verksamhetsområden

get_kpis_by_operating_area

Filtrera nyckeltal per verksamhetsområde

search_municipalities

Sök bland 290 kommuner och 21 regioner

get_municipality

Hämta detaljer via kommun-ID

get_municipality_groups

Lista kommungrupper

get_municipality_group

Hämta kommuner i en grupp

search_organizational_units

Sök skolor, äldreboenden m.m.

get_organizational_unit

Hämta enhetsdetaljer

get_ou_types

Lista enhetstyper

get_kpi_data

Hämta värden med könsfiltrering (T/M/K)

get_municipality_kpis

Lista KPI:er för en kommun

compare_municipalities

Jämför 2–10 kommuner

get_kpi_trend

Tidsserieanalys

analyze_kpi_across_municipalities

Statistik + rankning

filter_municipalities_by_kpi

Filtrera efter tröskelvärde

compare_kpis

Korrelation mellan nyckeltal

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
Kolada MCP Server - isakskogstad/kolada-mcp | VeilStrat