Agent Switchboard
M

MarkItDown

by Microsoft

VerifiedOfficial

Official listing: built and published by Microsoft. More from Microsoft

Converts PDF, Office, HTML, image, audio, and ZIP files into structured Markdown for LLM pipelines, preserving headings, lists, tables, and links.

Access
CLIMCP
Auth
None
Skills
5

Skills

  • Office Document Conversion

    Converts PDF, Word, PowerPoint, Excel, EPUB, and HTML files to Markdown while preserving headings, lists, tables, and links.

  • Image And Audio Extraction

    Reads EXIF metadata from images, runs OCR on them, and transcribes speech from WAV and MP3 audio files into Markdown.

  • MCP URI Conversion

    Serves a convert_to_markdown tool over STDIO, Streamable HTTP, or SSE that accepts http, https, file, and data URIs.

  • Azure Cloud Extraction

    Routes conversion through Azure Document Intelligence or Content Understanding for cloud OCR, layout analysis, and field extraction.

  • Third Party Plugins

    Loads third-party converter plugins with --use-plugins and lists installed ones, including LLM-vision OCR from markitdown-ocr.

Content & MediaData & Analyticsmarkdown-conversionpdf-extractiondocx-parsingocrspeech-transcriptionazure-document-intelligenceconverter-pluginspython-library
Visit Agent

Related Agents

PaddleOCR

API · CLI · MCP

Converts documents, receipts, and images into structured data with OCR, layout analysis, and table recognition, exposed…

VerifiedOfficialFeaturedby PaddlePaddle · Content & Media, Data & Analytics · 4 skills · No auth

Docling

API · CLI · MCP

Parses PDF, DOCX, PPTX, XLSX, HTML, audio, and image files into a unified DoclingDocument and exports Markdown, HTML…

Verifiedby IBM Research / LF AI & Data · Content & Media, Data & Analytics · 5 skills · No auth

Vidmoat

API · MCP

Edits video programmatically from agents over a remote MCP server and a REST v1 API: import media, run timeline…

Verifiedby Buzz Innovations Ltd · Content & Media, Voice & Messaging · 7 skills · API Key

OfficeCLI

CLI

Reads, edits, and creates Word, Excel, and PowerPoint files from the command line with no Office install — a single…

Verifiedby iOfficeAI · Content & Media · 3 skills · No auth
markitdown
Converts PDF, Office, HTML, image, audio, and ZIP files into structured Markdown for LLM pipelines, preserving headings, lists, tables, and links.
fields
nameMarkItDown
providerMicrosoft
urlhttps://github.com/microsoft/markitdown
categoriescontent-media · data-analytics
accesscli · mcp
authnone
streamingfalse
pushfalse
verifiedtrue
officialtrue · Microsoft
tagsmarkdown-conversion, pdf-extraction, docx-parsing, ocr, speech-transcription, azure-document-intelligence, converter-plugins, python-library
skills
office-document-conversionOffice Document ConversionConverts PDF, Word, PowerPoint, Excel, EPUB, and HTML f…
media-metadata-extractionImage And Audio ExtractionReads EXIF metadata from images, runs OCR on them, and …
mcp-uri-conversionMCP URI ConversionServes a convert_to_markdown tool over STDIO, Streamabl…
azure-enrichmentAzure Cloud ExtractionRoutes conversion through Azure Document Intelligence o…
converter-pluginsThird Party PluginsLoads third-party converter plugins with --use-plugins …
→ https://github.com/microsoft/markitdown