Kolada Se

Official registry Data and databases

Kolada (RKA) MCP — Sweden's municipal & regional key-performance-indicator (KPI) database.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code
claude mcp add --transport http kolada-se 'https://gateway.pipeworx.io/kolada-se/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "kolada-se": {
            "type": "http",
            "url": "https://gateway.pipeworx.io/kolada-se/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. mcp-kolada-se
  2. Tools
  3. Quick Start
  4. No MCP client? Call it over HTTP
  5. Standalone (no gateway account)
  6. Using with ask_pipeworx
  7. More
  8. License

mcp-kolada-se

Kolada (RKA) MCP — Sweden's municipal & regional key-performance-indicator (KPI) database.

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Tools

ToolDescription
search_kpiFind Kolada KPI (indicator) ids by title substring (Swedish). Searches ~5,000 indicators covering economy, schools, health, demographics, and personnel. Returns id, title, description, operating_area, and is_divided_by_gender. Use the returned id with get_data.
list_municipalitiesFind Sweden municipality/region ids by name substring. Returns id, title, and type ("K" = municipality of 290, "L" = region/landsting of 21). Use the returned id with get_data. Omit title to list all.
get_dataFetch numeric KPI values from Kolada for a specific indicator (kpiId), Swedish municipality or region (municipalityId), and year. Returns value rows broken down by gender: T=total, K=women (kvinnor), M=men (män); non-gendered KPIs return only T.municipalityId from list_municipalities. Returns values per gender ("T" total, "K" women, "M" men); non-gendered KPIs report only "T".
list_org_unitsKolada, the Swedish municipal and regional KPI database run by RKA — list the organizational units it tracks (schools, preschools, eldercare facilities) within one of Sweden's 290 municipalities or 21 regions. Returns id, title, municipality. OU ids can be used for unit-level data drilldowns. Filter by title substring and/or municipality id.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "kolada-se": {
      "url": "https://gateway.pipeworx.io/kolada-se/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/kolada-se/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1683+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/search_kpi \
  -H 'Content-Type: application/json' \
  -d '{"title":"arbetslöshet"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/search_kpi. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "kolada-se": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-kolada-se"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-kolada-se

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Kolada Se data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Frequently asked questions

What is Kolada Se?

Kolada (RKA) MCP — Sweden's municipal & regional key-performance-indicator (KPI) database.

How do I install Kolada Se?

It runs as a remote server. In Claude Code: claude mcp add --transport http kolada-se 'https://gateway.pipeworx.io/kolada-se/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Kolada Se need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is Kolada Se open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains Kolada Se?

It is published by pipeworx-io. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.