Agent Switchboard

Docling

by IBM Research / LF AI & Data

Verified

Parses PDF, DOCX, PPTX, XLSX, HTML, audio, and image files into a unified DoclingDocument and exports Markdown, HTML, DocTags, or lossless JSON for gen-AI pipelines.

Use it now

Keep it with up to 9 other tools you're setting up, then share them all as one link.

Try this first

Ask your assistant, with Docling connected:

  • Structured Document Export

    Use Docling to export parsed documents: ‹what you need›

  • VLM And ASR Pipelines

    Use Docling to run vision-language models: ‹what you need›

Connect it over MCP

Ask your coding agent to set it up

Connect Docling as an MCP server, following its setup instructions at https://docling-project.github.io/docling

Its page: docling-project.github.io/docling

Install the CLI

Install it as its own instructions say.

Its page: docling-project.github.io/docling

Call the API

Auth None needed

Its page: docling-project.github.io/docling

Compare

Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.

Access
APICLIMCP
Auth
None
Skills
5

Skills

  • PDF Layout Understanding

    Resolves page layout, reading order, table structure, code blocks, and formulas in PDFs, with OCR for scanned pages and images.

  • Multi Format Parsing

    Parses DOCX, PPTX, XLSX, HTML, EPUB, email, LaTeX, XBRL, and image files into one unified DoclingDocument representation.

  • Structured Document Export

    Exports parsed documents to Markdown, HTML, WebVTT, DocTags, or lossless JSON for chunking, indexing, and retrieval workflows.

  • VLM And ASR Pipelines

    Runs vision-language models such as GraniteDocling and speech recognition models to interpret images, charts, and audio tracks.

  • MCP And API Serving

    Serves conversions to agents through the docling-mcp server or the docling-serve HTTP API, running locally or against a remote endpoint.

Content & MediaData & AnalyticsResearch & Knowledgepdf-understandingtable-structure-recognitionocrdocling-documentgranite-doclingvision-language-modelsasr-transcriptionlangchain-integration
Visit Agent
docling
Parses PDF, DOCX, PPTX, XLSX, HTML, audio, and image files into a unified DoclingDocument and exports Markdown, HTML, DocTags, or lossless JSON for gen-AI pipelines.
try this first
Ask your assistant, with Docling connected:
Use Docling to export parsed documents: ‹what you need›structured-export
Use Docling to run vision-language models: ‹what you need›vlm-asr-pipelines
use it now
Connect Docling as an MCP server, following its setup instructions at https://docling-project.github.io/doclingmcp.setup-prompt
None neededapi.auth
fields
nameDocling
providerIBM Research / LF AI & Data
urlhttps://docling-project.github.io/docling
categoriescontent-media · data-analytics · research
accessapi · cli · mcp
authnone
streamingfalse
pushfalse
verifiedtrue
officialfalse
sponsoredfalse
tagspdf-understanding, table-structure-recognition, ocr, docling-document, granite-docling, vision-language-models, asr-transcription, langchain-integration
skills
pdf-layout-understandingPDF Layout UnderstandingResolves page layout, reading order, table structure, c…
multi-format-parsingMulti Format ParsingParses DOCX, PPTX, XLSX, HTML, EPUB, email, LaTeX, XBRL…
structured-exportStructured Document ExportExports parsed documents to Markdown, HTML, WebVTT, Doc…
vlm-asr-pipelinesVLM And ASR PipelinesRuns vision-language models such as GraniteDocling and …
mcp-and-api-servingMCP And API ServingServes conversions to agents through the docling-mcp se…
alternatives
/agents/docling/alternatives8 listedpaddleocr, markitdown, diarize-io
compare
/compare?a=docling&b=paddleocr&c=markitdownwith paddleocr, markitdown