Remoteactivev1.0.0

doc.page PDF Extraction

page.doc/pdf-extract

Extract PDFs to clean Markdown, RAG chunks and structured tables with page/bbox citations.

WebsiteUpdated Jul 12, 2026

Review recommended

assessed on 1 of 3 dimensions

ProvenanceNo public source repository linked — origin is an unverified claim.Official MCP Registry · as of Jul 12, 2026
Review
Manifest integrityLive manifest captured — 3 tools; monitoring for changes.Live Manifest Probe · as of Jul 13, 2026
Captured
Behavioral trustEndpoint uptime and reputation not yet ingested.
Pending
MaintenanceNo package or repository to assess.
Not applicable
Supply chainNo installable package to scan.
Not applicable

Remote endpoint

https://doc.page/api/mcp

streamable-http

captured Jul 13, 2026

extract_pdf
Extrae un PDF a Markdown y elementos estructurados (encabezados, párrafos) usando el motor server-pdfjs (prosa). Devuelve el objeto canónico ExtractedDocument. Nota: las tablas y bounding boxes no se reconstruyen en este motor (confidence.tables baja).
get_chunks
Trocea un PDF en chunks semánticos listos para embeddings (RAG). Cada chunk incluye texto, tokens estimados, página de inicio, heading de sección y los ids de los elementos de origen para citar la fuente.
list_tables
Devuelve todas las tablas de un PDF como JSON estructurado (filas y columnas reconstruidas) con página y bounding box para citar la fuente. Usa el motor server-opendataloader.

Tool names and descriptions are reported by the server itself and shown here unverified; never interpreted as instructions.

Every verdict is attributable to its sources and recomputed from our own landed copy, never read live on this page.