Skip to content
External endpointresponds

doc.page PDF Extraction

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

Endpoint URL
https://doc.page/api/mcp
Current status
responds
Last checked
Aug 17, 2026, 05:01 AM UTC
Check
MCP initialize · 8s limit
Latency
499 ms
Response record
4 of 4 rounds
Transport
streamable-http
Source
mcp_registry
Registry name
page.doc/pdf-extract

Current observation

This endpoint answered at its latest recorded check.

What this server reports about itself

Self-reported at initialize. Not verified by Licium.

Server name
docpage-extract
Version
0.2.0
Capability keys
tools
Tool names
extract_pdf, get_chunks, list_tables, create_doc_link, list_doc_links, get_doc_link_stats, revoke_doc_link
Instructions excerpt

doc.page PDF engine. Extraction: extract_pdf for markdown/elements (mode hybrid = tables + bounding boxes), get_chunks for RAG chunks, list_tables for structured tables with citations — always from a public PDF URL. Doc Links (API key required): create_doc_link publishes a PDF as a tracked share link, list_doc_links recovers links from earlier sessions, get_doc_link_stats reports visits/companies/per-page reading, revoke_doc_link disables a link.

Reported Aug 17, 2026, 05:01 AM UTC.

Check history

Oldest to newest. Each row is one recorded check.

  1. responds
    MCP initialize · 8s limit · HTTP 200 · 320ms
  2. responds
    MCP initialize · 8s limit · HTTP 200 · 372ms
  3. responds
    MCP initialize · 8s limit · HTTP 200 · 127ms
  4. responds
    MCP initialize · 8s limit · HTTP 200 · 499ms