
Connects Claude to Kosovo's official statistical database through the ASKdata PxWeb API. You get three tools: subjects to browse the database hierarchy, table_meta to inspect table schemas and valid dimension values, and query_table to pull actual data using PxWeb query objects. Results are capped at roughly 10,000 cells per query. Part of the Pipeworx gateway, so you can either hit this source directly or connect to the full gateway for 693+ data sources. Useful when you need programmatic access to Kosovo demographic, economic, or social statistics without manual CSV downloads or web scraping.
Kosovo Agency of Statistics (ASKdata) PxWeb MCP.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
subjects | Browse the Kosovo Agency of Statistics (ASKdata) PxWeb subject tree. Default path 'ASKdata' returns top-level folders (type 'l') and tables (type 't', '.px' suffix). Supply a deeper sub-path like 'ASKdata/Prices/Consumer Price Index' to drill into a subject area. |
table_meta | Fetch dimension definitions and valid coded values for a Kosovo ASKdata PxWeb table. Path must be the full path ending in '.px' (e.g. 'ASKdata/Prices/Consumer Price Index/Annual indicators/T4CPI.px'). Returns dimensions and value lists — required to build a valid query_table body. |
query_table | POST a PxWeb query to a Kosovo ASKdata table and return observations as json-stat2. body must be {query:[{code, selection:{filter,values}}], response:{format:'json-stat2'}}. PxWeb caps responses at ~10,000 cells — use codes from table_meta to narrow selections across dimensions. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"askdata-xk": {
"url": "https://gateway.pipeworx.io/askdata-xk/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/askdata-xk/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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
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 Askdata Xk data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
curl -X POST https://gateway.pipeworx.io/v1/tools/askdata_xk_subjects \
-H 'Content-Type: application/json' \
-d '{"path":"ASKdata"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/askdata_xk_subjects. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.