arquivo_search_pages
Pack: arquivo-pt · 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/arquivo_search_pages for the schema, then POST the same URL with its arguments for the data.
Full-text search of archived web pages in Arquivo.pt, the Portuguese web archive (captures since 1996), when the URL is unknown. Finds pages whose TEXT contains the given terms or a quoted phrase and returns, per hit, the page title, original URL, capture date, a text snippet with the matching terms, the archived (replay) URL, and links to the extracted text and a screenshot. Coverage: centred on the Portuguese web (.pt sites and Portuguese-language pages) but international English-language sites that Portuguese pages link to are captured too, probes for “climate change”, “quantum computing” and “Federal Reserve interest rates” return roughly 50M, 1M and 2M estimated hits, with ipcc.ch, microsoft.com and federalreserve.gov among the top results. The full-text index lags the crawl by years (probed 2026-10: most hits end in 2020, a few reach 2023) while arquivo_url_history carries current captures, so use that for anything recent at a known URL. Supports a date window (YYYY or YYYYMMDD), restricting to one site, restricting to a file type (pdf, html, doc), exclusion with a leading minus (Albert -Einstein), and paging by offset. Do not pass a URL as the query; use arquivo_url_history for that.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
query | string | yes | Search terms. Quote a phrase for an exact match (“inteligência artificial”); prefix a term with - to exclude it. Portuguese or English both work. Must not be a URL. |
from | string | no | Earliest capture date, as YYYY, YYYYMMDD or YYYYMMDDhhmmss. Default 1996. |
to | string | no | Latest capture date, as YYYY, YYYYMMDD or YYYYMMDDhhmmss. Omit it unless you need a window; the full-text index lags the crawl by years. |
site | string | no | Restrict hits to one site, e.g. “publico.pt” or “http://www.publico.pt”. |
type | string | no | Restrict to a file type by MIME subtype: pdf, html, doc, xls, ppt, rtf, ps. |
limit | number | no | Hits to return (default 10, max ${MAX_ITEMS}). |
offset | number | no | Hit offset for paging (default 0). The response carries next_offset when more hits exist. |
per_site | number | no | Maximum hits per site, to spread results across sources (default 2, the upstream default). Raise it to see more captures of the same site. |
Example call
Arguments
{
"query": "\"inteligência artificial\"",
"limit": 5
}
curl
curl -X POST https://gateway.pipeworx.io/arquivo-pt/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"arquivo_search_pages","arguments":{"query":"\"inteligência artificial\"","limit":5}}}'
TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('arquivo_search_pages', {
"query": "\"inteligência artificial\"",
"limit": 5
});
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 arquivo-pt pack
{
"mcpServers": {
"arquivo-pt": {
"url": "https://gateway.pipeworx.io/arquivo-pt/mcp"
}
}
}
See Getting Started for client-specific install steps.