Best MCP Servers for PDF & Document Processing (2026)
Servers that convert, extract, and process documents: MarkItDown converts PDFs and Office files to Markdown, MinerU handles complex layouts and OCR-heavy documents, Pandoc converts between dozens of formats, Content Core extracts from mixed media, and Nutrient provides a commercial document engine.
This page collects the 5 MCP servers in our directory that genuinely cover pdf & document processing — together they have 121,572 GitHub stars, and 0 of them run as hosted services you can connect to without installing anything. The highest-rated options are microsoft/markitdown, vivekvells/mcp-pandoc, lfnovo/content-core.
How to choose
Use MarkItDown for everyday conversion, MinerU for scanned or layout-heavy PDFs, Pandoc for format conversion at scale, and Nutrient when you need a supported commercial engine.
microsoft/markitdown
by microsoft
MarkItDown is Microsoft's lightweight Python utility for converting files to Markdown for use with LLMs and text-analysis pipelines, and this repository includes the markitdown-mcp package that exposes the converter through MCP. It converts PDF, PowerPoint, Word, Excel, images (EXIF metadata and OCR), audio (EXIF metadata and speech transcription), HTML, text-based formats such as CSV, JSON, and XML, ZIP files, YouTube URLs, and EPUBs, preserving document structure such as headings, lists, tables, and links.
npx -y microsoft-markitdownvivekvells/mcp-pandoc
by vivekVells
🗄️ 🚀 - MCP server for seamless document format conversion using Pandoc, supporting Markdown, HTML, PDF, DOCX (.docx), csv and more.
npx -y -y @smithery/clilfnovo/content-core
by lfnovo
🐍 🏠 - Extract content from URLs, documents, videos, and audio files using intelligent auto-engine selection. Supports web pages, PDFs, Word docs, YouTube transcripts, and more with structured JSON r
uvx content-coreopendatalab/MinerU-Ecosystem
by opendatalab
MinerU-Ecosystem is the official toolkit for the MinerU Open API, including a Python MCP server for document parsing. It converts PDFs, Word and PowerPoint files, images, spreadsheets, and web pages to Markdown or JSON with a VLM+OCR dual engine supporting 109 languages, formulas to LaTeX, and tables to HTML; the repository also ships a CLI, Python, Go, and TypeScript SDKs, and LangChain and LlamaIndex integrations.
uvx mineru-open-mcpPSPDFKit/nutrient-document-engine-mcp-server
by PSPDFKit
](https://glama.ai/mcp/servers/@PSPDFKit/nutrient-document-engine-mcp-server) 📇 🏠 🍎 🪟 🐧 - Self-hosted MCP server for Nutrient Document Engine. On-premises document processing with natural languag
npx -y @nutrient-sdk/document-engine-mcp-serverFrequently asked questions
What is the most popular MCP server for PDF & Document Processing?
microsoft/markitdown leads this list with 120,761 GitHub stars. MarkItDown is Microsoft's lightweight Python utility for converting files to Markdown for use with LLMs and text-analysis pipelines, and this repository includes the markitdown-mcp package that…
Are these PDF & Document Processing MCP servers free to use?
5 of the 5 servers here publish a license in the directory (MIT, Apache-2.0). 0 of them run as hosted services you can connect to remotely; the rest you install and run yourself. Hosted services may have their own pricing.
How do I choose an MCP server for PDF & Document Processing?
Use MarkItDown for everyday conversion, MinerU for scanned or layout-heavy PDFs, Pandoc for format conversion at scale, and Nutrient when you need a supported commercial engine.