Open-source document extraction with JSON output and MCP support

thisguyknowsai · x · 2026-07-20

Unstract’s open-source OCR/document-extraction stack turns documents into structured JSON without per-vendor templates, annotation, or model training.

It supports messy inputs such as invoices, contracts, bank statements, scans, handwriting, and images. The output can be deployed as a REST API or ETL pipeline, and it works with OpenAI, Claude, Gemini, Mistral, or local Ollama. It also ships with an MCP server for direct use in AI agents. The repo is AGPL-3.0 licensed and has 6.7k stars.

Original post →

More from coding & agent

coding & agent channel →