workflowstacks
mcp-server

unstract: Turn messy docs into structured JSON with LLM power

Extract data from PDFs, scans, and any unstructured source via API or ETL pipelines. Ideal for founders building AI‑driven data pipelines. 7.3k+ GitHub stars

From the repo · “LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows”

7,296 stars+13★ this week721 forksPythonGuide quality 8/10 · reviewed Oct 8Updated 10/21/2026100% 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.

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.
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
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/unstract && curl -fsSL https://workflowstacks.com/api/skills/unstract/claude-skill -o ~/.claude/skills/unstract/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How unstract: Turn messy docs into structured JSON with LLM power works
Codeflow
Free to inspect

Unstract: Turn messy docs into structured JSON with LLM power is a very large Python project (~256k lines across 1797 code files, plus 308 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, AGPL-3.0 license, has a test suite.

Size
Very large codebase
~256k lines · 1797 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Python · Docker
No API keys detected
Python 80%JavaScript 14%TypeScript 3%CSS 2%Shell 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    x2text-service/run.py
    Where the program starts running
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    unstract/connectors/README.md
    Inside unstract/ — the main logic begins here
What's in each folder
unstract/Core code — the actual logic460 files
backend/Backend / API934 files
frontend/Frontend / UI670 files
workers/Backend / API345 files
docs/Documentation47 files
docker/Deployment / infrastructure38 files
tools/Helper scripts27 files
platform-service/Folder25 files
READMEHas testsDocumentedCI checksDocker readyAGPL-3.0 licenseUpdated this month
Quick Actions
Details
Creator
Zipstack
Language
Python
Category
mcp-server
Published
2/21/2024

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/unstract.svg)](https://workflowstacks.com/skills/unstract?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 355,695
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 156,361
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 131,266
graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
mcp-server★ 79,404
OmniRoute: Unified AI Gateway Cutting Token Costs for Founders
OmniRoute lets startup founders access 290+ AI providers and 500+ models via a single endpoint, auto‑fallback and token‑saving compression. Ideal for teams building with Claude, GPT, Gemini, Copilot and more.
mcp-server★ 394
vigil
Vigil: The leading open source AI SOC. Apache 2.0. Runs against your own LLM, local or remote.
mcp-server★ 2,288
agent-teams-ai
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/GitHub Copilot/Kiro/Z.AI/MiniMax/Kimi(200+ models, 75+ LLM providers, free models no auth). Build your AI company with multiple teams