PDF Text, Table and OCR Extractor is an Apify Actor exposed through an MCP server for extracting text and tables from PDF documents, including scanned files requiring OCR. Developers can connect it to Claude, Cursor, and other AI agents for document-processing workflows.
Apify MCP server is a Frameworks & runtimes project. It focuses on extracting searchable text and structured tables from PDFs, including scanned documents, for downstream AI workflows. It is built as a B2B2C product for developers and AI agent builders. Apify MCP server is available on the web, the command line, and API.
Behind Apify MCP server is Apify, and it first shipped in 2025. The project is developed in the open on GitHub with 6.9k stars and 242 commits in the last 90 days. The category is crowded — PulseGate's index counts 20 comparable projects. Among its 8 catalogued features are PDF text extraction, table extraction, and OCR processing. It exposes integrations via an MCP server and a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do