Integration · Company data

Connect Claude & ChatGPT to Kolada

Ask your AI how Swedish municipalities and regions compare and get the numbers from Kolada. It searches key figures (KPIs) by name, reads their definitions and fetches values for one municipality, many municipalities or many years. It can also find organisational units such as schools and care homes and read their key figures.

Connect Kolada free

Free plan, no credit card. Takes about a minute.

Try asking

“Which Kolada key figures are about school costs?”
The AI searches KPIs by words in the title and lists matching key figures with their IDs.
“How has this key figure developed in Malmö over the years?”
It finds the municipality ID for Malmö and gets all years of the KPI for it.
“Compare the key figure for Uppsala, Västerås and Örebro for the last three years.”
It gets the KPI values for all three municipalities and years in one query and lays them out side by side.

What your AI can do

Key figures

Search KPIs and KPI groups by name and read each definition, unit and gender breakdown.

Municipalities and regions

Get values for one municipality, all municipalities in a year, a full history or any mix of KPIs, places and years.

Units and groups

Find schools, care homes and other organisational units, and municipality comparison groups, and read their key figures.

“Which municipality had the highest value for this KPI last year?”
It gets the KPI for all municipalities in that year and sorts the values.
“What does this KPI measure, and is it split by gender?”
It reads the KPI definition, including description, unit and whether it is broken down by gender.
“Find the schools in Lund and show this key figure for them.”
It searches organisational units in the municipality and fetches the KPI values for those units.

23 tools for Kolada

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

get_kpiGet the definition of one or more KPIs by `kpi_id` (comma-separated IDs), including description, unit and whether it is broken down by gender.
get_kpi_by_yearGet one KPI for all municipalities in a given year, by `kpi_id` and `year`; `region_type` narrows to municipalities or regions.
get_kpi_dataGet KPI values filtered by any combination of `kpi_id`, `municipality_id` and `year` (each a list). Use this for comparisons across municipalities or years.
get_kpi_groupGet one KPI group by `kpi_group_id`, with the KPIs it contains.
get_kpi_historyGet all years of one KPI for one municipality, by `kpi_id` and `municipality_id`.
get_kpi_ouGet one ou for a kpi by ou id. Results are paginated. API summary: Get unit-data by kpi-id and unit-id.
get_kpi_unit_data_by_yearGet one KPI for all organisational units in a year, by `kpi_id` and `year`, optionally within one `municipality_id`.
get_kpi_valueGet the value of one KPI for one municipality and year, by `kpi_id`, `municipality_id` and `year`.
get_municipalityGet one municipality or region by `municipality_id`.
get_municipality_dataGet all KPI values for one municipality in one year, by `municipality_id` and `year`.
get_municipality_groupGet one municipality group by `municipality_group_id`, with its member municipalities.
get_municipality_kpiGet one kpi for a municipality by kpi id. Results are paginated. API summary: Get data by using kpi-id and municipality.
get_municipality_year_get_ou_data_kpis_per_municipality_oudata_mGet one year for a municipality by year. Results are paginated. API summary: Get unit-data by year and municipality. All OUs for the municipality are returned.
get_ou_kpiGet one kpi for a ou by kpi id. Results are paginated. API summary: Get unit-data by kpi-id and unit-id.
get_ou_yearGet one year for a ou by year. Results are paginated. API summary: Get unit-data by kpi-id, year and unit-id.
get_unitGet one organisational unit by `ou_id`.
get_unit_dataGet KPI values for organisational units filtered by `ou_id`, `kpi_id` and `year`.
get_unit_data_by_year_and_unit_idGet one year for a ou by year. Results are paginated. API summary: Get unit-data by year and unit-id.
search_kpi_groupsSearch groups of related KPIs by `title`.
search_kpisSearch Kolada key figures (KPIs) by words in the `title`, e.g. 'skola' or 'kostnad'. Returns KPI IDs for data lookups.
search_municipalitiesSearch Swedish municipalities and regions by `title` (name), optionally limited by `region_type` (municipality or region). Returns their IDs.
search_municipality_groupsSearch groups of municipalities (e.g. comparison groups) by `title`.
search_unitsSearch organisational units such as schools or care homes by `title`, optionally within a `municipality`. Returns unit IDs.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Kolada from the app list.
2
Paste your key
No account or API key needed. Kolada data is open, so you only pick the app in PipMCP to get your MCP link.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Kolada?

It can search KPIs, KPI groups, municipalities, municipality groups and organisational units, read their details and fetch KPI values by municipality, unit and year. All tools only read.

Does the AI see my Kolada credentials?

There are none to see. The Kolada API needs no account or API key, so you do not paste anything into PipMCP. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on. All tools here only read public statistics, so nothing is changed anywhere. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT, open Settings › Apps & Connectors › Advanced, turn on Developer mode and add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. Kolada's data itself is open and free.

Do I need to know the KPI IDs?

No. Every key figure, municipality and unit has an ID in Kolada, but the AI finds them for you. It searches by words in the title, such as a municipality name or a topic, and then uses the IDs to fetch the values.