nplg_search
Pack: nplg-catalog · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)
No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/nplg_search for the schema, then POST the same URL with its arguments for the data.
Search the union catalogue of the National Parliamentary Library of Georgia by keyword, title, author or subject. Returns the true number of matching records alongside the page of citations, each with its permanent bib id, title (Georgian with a parallel Latin title where the record carries one), author, imprint and material type. Queries work in Georgian (მხედრული) or Latin script. Narrow by material with scope (books, periodicals, maps, dissertations, archival documents…). Pages 50 at a time via offset.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
query | string | yes | Search terms. Georgian or Latin script both work; “and”/“or”/“not” are honoured. |
index | string | no | Which index to search: keyword (default), title, author, subject. |
scope | integer | no | Material scope, 1-11. 1 = entire collection (default), 2 books, 3 periodicals, 4 posters and prints, 5 cartographical, 6 electronic, 7 dissertations, 8 music and audio, 9 archival documents, 10 newspaper articles, 11 journal articles. |
offset | integer | no | Zero-based record offset for paging; the page size is 50. Pass 50 for the second page. |
Example call
Arguments
{
"query": "tbilisi"
}
curl
curl -X POST https://gateway.pipeworx.io/nplg-catalog/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"nplg_search","arguments":{"query":"tbilisi"}}}'
TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('nplg_search', {
"query": "tbilisi"
});
More examples
{
"query": "tbilisi",
"index": "title",
"offset": 50
}
Connect
Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:
{
"mcpServers": {
"pipeworx": {
"url": "https://pipeworx.io/mcp"
}
}
}
Connect to just the nplg-catalog pack
{
"mcpServers": {
"nplg-catalog": {
"url": "https://gateway.pipeworx.io/nplg-catalog/mcp"
}
}
}
See Getting Started for client-specific install steps.