Pricing

Pay per usage

Go to Apify Store

Mcp Document Converter

Try for free

Pricing

Pay per usage

Rating

0.0

(0)

Developer

Donny Nguyen

Actor stats

Bookmarked

Total users

Monthly active users

19 hours ago

Last modified

Features

Convert any webpage to Markdown, plain text, or clean HTML
Batch processing of multiple URLs in a single run
Intelligent content extraction that removes navigation, ads, and sidebars
Configurable image and link inclusion in output
Word count and content length metrics for each conversion
MCP-compatible output format for AI agent integration

How It Works

The actor fetches the target URL, extracts the main content area, strips unnecessary elements (scripts, styles, navigation), and converts the remaining content to the specified output format. It intelligently identifies the main content area using common selectors like main, article, and .content.

Input Configuration

Parameter	Type	Default	Description
`url`	string	`https://docs.apify.com/platform/actors`	Single URL to convert
`urls`	array	`[]`	Multiple URLs for batch conversion
`outputFormat`	string	`markdown`	Output format: markdown, text, or html
`includeImages`	boolean	`true`	Include image references in output
`includeLinks`	boolean	`true`	Include hyperlinks in output

Output Format

Each converted document produces a dataset item with:

url - Source URL of the document
title - Page title extracted from HTML
outputFormat - The format used for conversion
content - The converted document content
contentLength - Character count of the output
wordCount - Word count of the output
convertedAt - ISO timestamp of conversion

Use Cases

AI Agent Document Processing: Feed webpage content to LLMs in clean Markdown format
Content Migration: Convert web content for use in documentation systems
Research Automation: Extract and convert multiple research papers or articles
Knowledge Base Building: Convert web resources into structured text for RAG systems
Content Archival: Save clean versions of webpages without clutter

API Integration

You can call this actor via the Apify API to integrate document conversion into your workflows. Use the MCP server endpoint for direct AI agent access, or call the actor programmatically from any language.

Pricing

This actor uses pay-per-event pricing. Each document conversion counts as one event. Visit the Apify platform for current pricing details and to manage your subscription.

Pandoc Universal Mcp

whitewalk/pandoc-universal-mcp

Convert documents between 40+ formats via MCP. Markdown, DOCX, PDF, HTML, LaTeX, EPUB, PPTX & more. Academic support with citations, bibliography & math. Batch conversion. Perfect for AI agents & Claude Desktop integration.

seena Singh

Markitdown Mcp Server

rector_labs/markitdown-mcp-server

Cloud-hosted MCP server converting 29+ document formats (PDF, DOCX, PPTX, images, audio) to AI-ready Markdown. Zero Python setup. Perfect for RAG pipelines and AI agents. Pay-per-use: $0.02/conversion. Built on Microsoft's Markitdown (82k+ ⭐).

RECTOR SOL

Markdown to PDF MCP Server

parseforge/markdown-to-pdf-mcp

Convert Markdown content to PDF format using Model Context Protocol (MCP). Perfect for developers, content creators, and businesses who need to programmatically convert Markdown documents to professional PDFs with custom styling, page sizes, margins, and orientations.

ParseForge

5.0

(2)

PDF To JSON Parser

parseforge/pdf-to-json-parser

Convert PDF documents into structured JSON using AI-powered OCR and smart data extraction. The Actor processes every page to ensure complete coverage, then identifies text, fields, tables, and key details, delivering clean, organized JSON ready for automation or analysis.

ParseForge

5.0

(1)

MCP Documentation Hunter

bmerlyns/merlyn-docs-hunter

Enhance your coding assistants with up to date documentation of the frameworks or codebases you use. Actor to be called via MCP and provide realtime data to the coding assistant -> improving LLM's context and reducing hallucinations.

Benjamin Merlyn

Obsidian Mcp Actor

breezy_overthrow/obsidian-mcp-actor

A lightweight Obsidian MCP Actor built for fast, local note automation. It parses, indexes, and transforms vault content with zero bloat. Perfect for workflows that need speed, clean structure, and reliable processing across markdown files, tags, metadata, and linked notes.

Antony mwangi

Doc To Markdown MCP Server

abotapi/doc-to-markdown-mcp

An MCP server that converts documents to clean Markdown. Convert PDFs, Word docs, Excel spreadsheets, PowerPoints, HTML, images, and more to AI-friendly Markdown format.

AbotAPI

PDF MCP Server

constant_quadruped/pdf-mcp-server

Stateless PDF tools exposed via MCP. Open, split, merge, extract text, fill and flatten forms, and generate PDFs in a single run. Designed for deterministic, auditable document transformations by agents and workflows.

PDF Intelligence

marielise.dev/pdf-intelligence

Stop fighting PDFs. Extract text, tables, and insights from any document, scanned or digital. Get RAG-ready chunks for LangChain & LlamaIndex. AI-powered summaries, classification, entity extraction. Use our API keys or bring your own (50% discount). From PDF chaos to clean data in minutes.

Marielise

HWP.works - Korean Document Processing API & MCP Server

lurid_alley/hwp-works

Cross-platform HWP/HWPX document processing API with MCP support. Extract text, tables, metadata from Korean HWP documents. Fill templates, edit paragraphs, compare documents. Works on any platform — no Windows required.