OECD MCP server for AI research

About this source

Search OECD datasets, inspect dimensions and query series across member countries. Dimension-heavy data: keep units and provenance in your write-up.

Type them into Kahubi’s chat once the source is connected.

“How does public spending on early childhood education compare across the Nordic OECD countries?”

What comes back: Series values with the dataset, measure and unit named.

“Show health expenditure as a share of GDP for Germany, France and Sweden since 2010.”

What comes back: Yearly values with the OECD dataset and measure definitions.

The 7 tools this server offers to Kahubi. The assistant picks the right one for each question.

oecd_list_agencies
List OECD SDMX agencies, the directorate each belongs to, and the number of dataflows each publishes.
oecd_search_datasets
Search OECD dataflows by keyword or theme, matching against dataflow names and descriptions.
oecd_get_dataset_info
Fetch a dataflow's dimensions, their order, and how to construct a query key.
oecd_get_dimension_values
Fetch the valid codes and labels for one dimension of a dataflow.
oecd_query_dataset
Fetch observations from an OECD dataflow filtered by a dimension key and optional time range.
oecd_dataframe_describe
List tables and columns staged on a DataCanvas by a prior oecd_query_dataset spill.
oecd_dataframe_query
Run a read-only SQL SELECT against OECD observation tables staged on a DataCanvas by oecd_query_dataset.

Community server. An open-source server maintained by the MCP community. Kahubi tests it with live queries before listing it and health-checks it regularly.
Cited, checkable answers. Results are treated as retrieved material and cited with the source’s own identifiers, so you can open every record the answer relied on.
Your files stay private. Only the search the assistant writes for your question is sent to OECD.