Arquivo Pt MCP server

@pipeworx/arquivo-pt

Full-text search of archived web pages in Arquivo.pt, the Portuguese web archive run by FCCN (captures since 1996). Where the Internet Archive's Wayback Machine (pack wayback) needs the URL, Arquivo.pt indexes the text of what it captured, so a caller can find archived pages by phrase, then read a capture's extracted text or list every preserved version of a URL.

Part of Pipeworx — an MCP gateway connecting AI agents to 1743+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

— full-text hits for terms or a quoted phrase: title, original URL, capture date, decoded snippet, archived replay URL, extracted-text and screenshot links, plus estimatedtotal and nextoffset. Zero hits answer found:false with reason:"no_match" and a hint.

• arquivosearchpages(query, from?, to?, site?, type?, limit?, offset?, per_site?)

capture of a domain, host or full URL, newest first, with capture timestamp, crawl HTTP status, MIME type, size, digest and replay links. Zero captures answer found:false with reason:"no_captures".

• arquivourlhistory(url, from?, to?, limit?, offset?) — every preserved

extracted from one capture (originalurl + capturedatts of a hit). A capture that does not exist answers found:false, reason:"capturenot_found".

• arquivopagetext(url, timestamp, max_chars?) — the plain text Arquivo.pt

Every response carries source (the exact upstream URL) and dataasof. A transport failure, a non-JSON body or a changed response shape throws a loud error naming Arquivo.pt and the HTTP status — never an empty list.

Auth

Keyless.

Coverage, honestly

but international pages linked from them are captured too. Probed 2026-10-08: "climate change" ≈ 52-53M estimated hits (academia.edu, eea.europa.eu, ipcc.ch), "quantum computing" ≈ 0.8-1.1M (techtarget.com, microsoft.com, en.wikipedia.org), "Federal Reserve interest rates" ≈ 1.8-1.9M (federalreserve.gov, vox.com). The estimate varies by index node. English queries work; the top hits skew to pages Portuguese sites cite.

• Centred on the Portuguese web (.pt sites and Portuguese-language pages),

search restricted to from=2022 returns 0 hits on most calls, one node answered with 2023 captures, and arquivourlhistory lists captures from mid-2026. Use the URL history for anything recent.

• The full-text index lags the crawl by years. Probed 2026-10-08, a

Cloudflare Worker on 2026-10-08 the same URL returned, minutes apart: real hits in 30-37 s; real hits in 1-6 s with FAWP collection ids and a hostKey field; responseitems: [] with estimatednrresults 3.5M; and responseitems: [{}, {}, {}] (429 bytes, every row empty) — the last one for every unquoted multi-word query for a stretch, while a laptop got real hits for the identical URL and a quoted phrase answered correctly from the Worker. The pack retries once with maxItems nudged and then throws an error naming the fault; rows with no URL/timestamp are never returned as hits (droppedmalformed_rows counts them). Some nodes also ignore maxItems (9 rows for 5); hits are capped at limit.

• Arquivo.pt load-balances across index nodes that disagree. From a live

previous calendar year) already covers the whole index, and forcing to= made the same query return zero items from a live Worker while estimatednrresults stayed at 3.8M (probed twice, 2026-10-08).

• The pack sends to only when you pass one. The upstream default (the

more captures of one site.

• Hits are deduplicated to 2 per site by default (per_site); raise it to see

Data sources

Shortened. The full README is on GitHub.