page.doc/pdf-extractsearch

doc.page PDF Extraction

Synced · awaiting check

Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.

Install

claude mcp add --transport http pdf-extract https://doc.page/api/mcp

Requires: Authorization

Our take

This server extracts PDFs into Markdown, chunks, and cited tables, then publishes tracked document links with reader stats. It is for document-heavy agent workflows such as ingestion, retrieval prep, and lightweight publishing. The feature set is practical, but it mixes extraction and hosted distribution, so teams with stricter data-handling requirements should check where content is processed and stored.

reviewed by hand · 2026-07-30

Something wrong or dead here? Report it

Verification record

last verified: yesterday
in registry since: 2026-07-13

More in search

mcp-server-searchsearch

mcp-server-search

Verified · 13 days ago

MCP server for web search operations

hand-reviewed39k stars105 dl/wkchecked 13 days ago

screenpipe-mcpsearch

screenpipe

Verified · 5 days ago

Search your local screen recordings, audio transcripts, and computer activity from screenpipe.

hand-reviewed21k starschecked 5 days ago

sui-kapasearch

Sui Knowledge Base (kapa.ai)

Verified · 4 days ago

Semantic search across Sui documentation and knowledge sources, powered by kapa.ai

hand-reviewed7.7k starschecked 4 days ago

firecrawl-mcp-serversearch

Firecrawl MCP Server

Verified · 16 days ago

MCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.

hand-reviewed7.2k starschecked 16 days ago

searchsearch

Airweave Search

Verified · 14 days ago

MCP server for searching Airweave collections with natural language queries.

hand-reviewed6.5k stars1.6k dl/wkchecked 14 days ago

claude-code-explorer-mcpsearch

Claude Code Explorer MCP

Verified · 7 days ago

Explore the Claude Code CLI source — browse tools, commands, search code, and more.

hand-reviewed6.2k stars52 dl/wkchecked 7 days ago