harumiWeb/exstruct

Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading and writing by AI agents through MCP integration.

66
/ 100
Established

Implements platform-aware extraction with graceful fallbacks: COM-based rich extraction on Windows, LibreOffice UNO bridge on Linux/macOS, and safe degradation to cells-only when neither is available. Provides three operational interfaces—Python API, JSON-first CLI with dry-run/patch workflows, and MCP server—allowing teams to choose between direct imperative editing, declarative patch-based automation, or sandboxed host-managed integrations. Includes tunable table detection heuristics, formula maps, hyperlink extraction, and optional PDF/image rendering tied to extraction granularity.

128 stars and 3,058 monthly downloads. Available on PyPI.

Maintenance 13 / 25
Adoption 18 / 25
Maturity 18 / 25
Community 17 / 25

How are scores calculated?

Stars

128

Forks

20

Language

Python

License

BSD-3-Clause

Category

excel-automation-mcp

Last pushed

Mar 11, 2026

Monthly downloads

3,058

Commits (30d)

0

Dependencies

7

GitHub PyPI
Excel Automation Mcp · 1 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/harumiWeb/exstruct"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Explore RAG Tools

All categories Trending RAG directory Insights