Extract text from a document

Read a public or provided document and return requested text or fields.

Also asked as: read PDF, document extraction.

Guide

Best free ways to extract text from a PDF with an AI assistant

Websites for this task

Github

github.com · browser_only

Extend

www.extend.ai · browser_only

Discovery signals are dated scans of files a site publishes; they do not show whether an agent can finish the task there. Method.

Agents: find_sites({"task":"extract-pdf-text"}).

APIs and MCP servers in the catalog

LlamaParse

Document parsing API from LlamaIndex for turning files into structured data for agents and RAG pipelines.

Documents and OCR

Unstructured

Document transformation API and MCP interface for parsing and structuring files for downstream AI use.

Documents and OCR · MCP

Reducto

Document parsing and extraction API for converting complex files into structured outputs.

Documents and OCR

Extend

Document parsing, extraction, classification, and form-filling API, billed in credits.

Documents and OCR

Landing AI

Document intelligence APIs and agent tools for extracting structured data from documents, with official MCP support.

Documents and OCR · MCP

Affinda Resume Parser

Official Affinda REST API for parsing resumes and other documents into structured data, authenticated with an API key, with Python and Node.js SDKs.

Documents and OCR

Context7

Up-to-date docs for AI agents.

Docs and reference servers · MCP

Hugging Face MCP

Official Hugging Face documentation for using Hugging Face with MCP.

Docs and reference servers · MCP

MCP reference servers

Reference MCP server implementations from the Model Context Protocol project.

Docs and reference servers · MCP

Agents: search_tools({"query":"read PDF"}). All tasks · updated 2026-11-21.