# Documents and OCR

7 tools for agents in documents and ocr: APIs, official MCP servers and Actors. Family: Content and media.

Tasks: [Extract text from a document](https://agentready-tools.com/task/extract-pdf-text.md), [Extract fields from an invoice](https://agentready-tools.com/task/extract-invoice-fields.md).

## Compare

| Tool | MCP | Pricing | Jurisdiction | Agent-readiness |
|---|---|---|---|---|
| [Affinda Resume Parser](https://agentready-tools.com/tools/affinda) | No | Not yet verified | - | Not enough data |
| [Extend](https://agentready-tools.com/tools/extend) | No | Pay-as-you-go includes 10,000 credits ($100) free, then $0.01 per additional credit | - | Not enough data |
| [Landing AI](https://agentready-tools.com/tools/landing-ai) | Yes | Free tier includes 1,000 credits and does not require a credit card | - | Not enough data |
| [LlamaParse](https://agentready-tools.com/tools/llamaparse) | No | Pay-as-you-go includes 10,000 free credits, then $1.50 per 1,000 credits | - | Not enough data |
| [Reducto](https://agentready-tools.com/tools/reducto) | No | $150 in free usage credits, then per-page rates | - | Not enough data |
| [Textkernel Tx Platform](https://agentready-tools.com/tools/textkernel-tx-platform) | No | Not yet verified | - | Not enough data |
| [Unstructured](https://agentready-tools.com/tools/unstructured) | Yes | First 10,000 pages are free, then $0.015 per page | - | Not enough data |

Comparison fields come from the catalog listing. "Not yet verified" and "Not enough data" mean we have no checked value yet; nothing is guessed.

## Tools

- [Affinda Resume Parser](https://agentready-tools.com/tools/affinda): Official Affinda REST API for parsing resumes and other documents into structured data, authenticated with an API key, with Python and Node.js SDKs.
- [Extend](https://agentready-tools.com/tools/extend): Document parsing, extraction, classification, and form-filling API, billed in credits.
- [Landing AI](https://agentready-tools.com/tools/landing-ai) (MCP): Document intelligence APIs and agent tools for extracting structured data from documents, with official MCP support.
- [LlamaParse](https://agentready-tools.com/tools/llamaparse): Document parsing API from LlamaIndex for turning files into structured data for agents and RAG pipelines.
- [Reducto](https://agentready-tools.com/tools/reducto): Document parsing and extraction API for converting complex files into structured outputs.
- [Textkernel Tx Platform](https://agentready-tools.com/tools/textkernel-tx-platform): Official Textkernel Tx Platform API for resume (CV) and job description parsing, candidate matching, and skills data, authenticated with account ID and…
- [Unstructured](https://agentready-tools.com/tools/unstructured) (MCP): Document transformation API and MCP interface for parsing and structuring files for downstream AI use.

JSON: https://agentready-tools.com/categories/documents-ocr.json. MCP: `search_tools({"category":"Documents and OCR"})`. All categories: https://agentready-tools.com/categories.md. Updated 2026-11-22.
