mcp-server

unstract: Extract Data

Name: unstract: Extract Data
Author: Zipstack

Get structured data from unstructured sources with unstract, built for startup founders and data engineers.

6,692 stars632 forksPythonQuality 8/10Updated 7/8/2026100% free · open source

What it does

Unstract extracts structured data from unstructured sources like documents and text using large language models, making it easier to integrate into API deployments and ETL pipeline workflows.

Install / run

pip install unstract

When to use it

•You need to automate data extraction from invoices, receipts, or contracts.
•Your startup relies on manual data entry from unstructured text data.
•You're building an ETL pipeline that requires extracting specific data points from large documents.

Quick start

1Clone the unstract repository: git clone https://github.com/Zipstack/unstract.git
2Navigate to the unstract directory: cd unstract
3Run the example extractor: python examples/extractor.py
4Modify the extractor configuration in config.json to suit your specific use case
5Test your custom extractor with a sample document: python examples/extractor.py --input example.pdf

Ready-to-paste prompt

python examples/extractor.py --input example.pdf --output extracted_data.json --config config.json

Heads up: Make sure you have the necessary large language model dependencies installed and configured, as unstract relies on these models for data extraction.

Saves to your device