# zcaceres/markdownify-mcp

A Model Context Protocol server for converting almost anything to Markdown

Repository: https://github.com/zcaceres/markdownify-mcp
Canonical: https://ross.abutalabs.com/products/markdownify-mcp
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, anthropic, anthropic-ai, anthropic-claude, markdown, mcp, model-context-protocol, ocr, tools
Last push: 2026-08-11T05:23:40+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 81, longevity 44
- inputs: {"age_days": 623, "days_push": 22, "days_rel": 124, "gap_med": 9.0, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2983, forks 253 (observed 2026-08-28T04:07:33.912297+00:00)

## What it is
A Model Context Protocol (MCP) server that converts PDFs, images, audio, Office documents, and web content (including YouTube transcripts and web pages) into Markdown. It exposes these conversion tools to MCP clients like Claude Desktop.

## Use cases
- convert pdfs to markdown
- transcribe audio files to text
- extract youtube video transcripts
- convert docx and pptx files to markdown
- scrape web pages into markdown
- ocr images to markdown text
- give claude access to document conversion tools

## When to choose
- you use an MCP client like Claude Desktop and want document-to-markdown conversion
- you need a single tool handling PDFs, Office files, images, audio, and web pages
- you want YouTube transcript extraction integrated with your AI workflow

## When to avoid
- you need a standalone CLI converter without an MCP server
- you only need simple HTML-to-markdown conversion
- you cannot install Python (markitdown) and Node/Bun dependencies

## Facets
- artifact type: service
- maturity: active
- function: mcp, markdown, ocr, pdf, speech-recognition, web-scraping, parser
- domain: developer-tools, artificial-intelligence, pdf, files
- platform: bun, cross-platform, cli
- tags: mcp-server, markdown-conversion, file-conversion, youtube-transcripts, markitdown, document-conversion, natural-language-processing, nodejs, docker

## Member repositories
- zcaceres/markdownify-mcp (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:33.912297+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:31:28.041791+00:00, confidence not recorded.
  - readme: https://github.com/zcaceres/markdownify-mcp (fetched 2026-08-28T04:07:33.912297+00:00, sha 35b092d4f3ce)
- Data as of 2026-08-30T08:39:29.467469+00:00.