Unfragile

Docling is not among the candidate products: source 1 is an IBM conference lab page with no indexed actions, so it is not confirmed to be Docling. The closest candidates that parse and convert documents to structured data are listed below, with PyMuPDF first for PDF-to-structured-text extraction.

1
PyMuPDFpymupdf.iofound in code, not yet checked
Fast Python library that extracts structured content from PDFs and exposes a PDF-to-Markdown conversion action for AI and extraction workflows 515.
Website Get started
for agents: convert_pdf_to_markdown
2
Xbergxberg.ioverified and signed
Self-hostable document intelligence platform that extracts text, tables and metadata from 91+ document formats via its kreuzberg action 717.
Website Docs Pricing
+1 community tools built for it
for agents: kreuzberg · parser · converter
3
Nutrientnutrient.ioverified and signed
Document SDK and APIs with a parse_document action that extracts structured data from documents 616.
Website Docs Pricing Get started
for agents: nutrient-document-processing · parse_document · document_processor
4
Asposeaspose.comverified and signed
File format SDKs for .NET, Java, C++ and Python that create, edit and convert document formats, including DOCX and PDF conversion 414.
Website Docs Pricing Get started
for agents: DOCX · file_convert_to_pdf · PDF
5
Artifexartifex.comfound in code, not yet checked
Document processing technology vendor (including MuPDF and PyMuPDF) offering pdf_info and read_pdf actions to extract PDF content 919.
Website Docs
+2 community tools built for it
for agents: pdf_info · read_pdf

Sources

1IBMibm.com · read 2026-10-29
4File Format SDKs for Word Excel PDF Email PowerPoint Barcode Images OCR Note and 3Daspose.com · read 2026-10-29
5PyMuPDF 2.0: Turn PDF Documents into Structured Datapymupdf.io · read 2026-10-30
6Nutrient — Document layer for agents | PDF SDKs and APIsnutrient.io · read 2026-10-29
7Xberg — document intelligence & RAGxberg.io · read 2026-10-30
9Artifex | Open Source Power, Enterprise Performanceartifex.com · read 2026-10-30
14Aspose.Words for .NET: declares "DOCX" (the record we read and signed)unfragile.ai · read 2026-10-24
15pymupdf4llm-mcp: declares "convert_pdf_to_markdown" (the record we read)github.com · read 2026-10-24
16nutrient-document-processing: declares "nutrient-document-processing" (the record we read and signed)unfragile.ai · read 2026-10-24
17kreuzberg: declares "kreuzberg" (the record we read and signed)unfragile.ai · read 2026-10-24
19gigatext: declares "pdf_info" (the record we read)github.com · read 2026-10-24

For agents: the 10 actions behind this answer

· IBM Techxchange2025 Lab3640 Docling website read, tools not yet checked
For more than a century, IBM has been a global technology innovator, leading advances in AI, automation and hybrid cloud solutions that help businesses grow.
dotnet-pinvoke · dotnet-pinvoke verified and signed
Correctly call native (C/C++) libraries from .NET using P/Invoke and LibraryImport. Covers function signatures, string marshalling, memory lifetime, SafeHandle, and cross-platform patterns. USE FOR: writing new P/Invoke or LibraryImport declarations, reviewing or debugging existing native interop co
pdftk-server · pdftk-server verified and signed
Skill for using the command-line tool pdftk (PDFtk Server) for working with PDF files. Use when asked to merge PDFs, split PDFs, rotate pages, encrypt or decrypt PDFs, fill PDF forms, apply watermarks, stamp overlays, extract metadata, burst documents into pages, repair corrupted PDFs, attach or ext
DOCX · Aspose.Words for .NET verified and signed
convert_pdf_to_markdown · pymupdf4llm-mcp found in code, not yet checked
nutrient-document-processing · nutrient-document-processing verified and signed
Process documents with Nutrient DWS Processor. Use for PDF generation and conversion, packet assembly, OCR, Processor JSON-content extraction, staged redaction, watermarking, signing, password protection, optimization, PDF/A, or PDF/UA output. Route high-fidelity markdown or spatial parsing to Nutri
kreuzberg · kreuzberg verified and signed
Extract text, tables, metadata, and images from 91+ document formats (PDF, Office, images, HTML, email, archives, academic) using Kreuzberg. Use when writing code that calls Kreuzberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR,
convert_document · document-mcp found in code, not yet checked
Converts a document from one supported format to another via documents.js's DocumentConverter port -- docx, pptx, xlsx, odt, odp, ods, odg, odf, markdown, and pdf. Not every (source, targetFormat) pair is supported directly (odf, for instance, only ever converts to pdf); call list_document_conversio
pdf_info · gigatext found in code, not yet checked
Return metadata and per-page analysis for a PDF.
PDFsharp · PDFsharp for Windows and Linux verified and signed

Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.