PDF Text, Table and OCR Extractor

Overview

PDF Text, Table and OCR Extractor is a Model Context Protocol server that converts PDF URLs into structured data. It extracts per-page text, tables formatted as rows, Markdown output, document metadata, and performs OCR on scanned pages, making PDF content accessible to AI assistants as tools they can invoke directly.

This is a hosted remote server — connect your MCP client to https://mcp.apify.com/?tools=brenton8907/pdf-text-table-ocr-extractor with no local installation required. Authentication is not needed. The latest release is v0.1.0, maintained at https://apify.com/brenton8907/pdf-text-table-ocr-extractor.

PDF Text, Table and OCR Extractor is listed in the File System category and works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and other MCP clients. If you maintain this server, claim this listing to verify ownership and keep information current.

Installation

Settings → Connectors → Add custom connector
Name: PDF Text, Table and OCR Extractor
URL:  https://mcp.apify.com/?tools=brenton8907/pdf-text-table-ocr-extractor