Advanced MarkItDown MCP server with PaddleOCR support for PDF, images, and Office documents
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"markitdown-mcp-advanced","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# MarkItDown MCP Advanced A powerful MCP (Model Context Protocol) server that converts various document formats to Markdown with PaddleOCR support. ## Features - **Multi-format Support**: PDF, images, Office documents, HTML, CSV - **OCR Integration**: High-accuracy text recognition via PaddleOCR API - **URL Support**: Direct processing of remote file URLs - **MCP Protocol**: Full compliance with MCP standard (STDIO and HTTP modes) - **Lightweight**: Core features use only Python standard library ## Supported Formats | Category | Extensions | |----------|------------| | PDF | `.pdf` | | Images | `.png`, `.jpg`, `.jpeg`, `.gif`, `.bmp`, `.tiff`, `.webp` | | Word | `.docx` | | PowerPoint | `.pptx` | | Excel | `.xlsx`, `.xls` (requires extra dependency) | | Web | `.html`, `.htm` | | CSV | `.csv` | ## Configuration Required environment variables: ```bash export PADDLE_API_URL="your_api_url" export PADDLE_TOKEN="your_token" export MARKITDOWN_TEMP_DIR="/path/to/temp" ``` ## Usage with Claude Desktop Add to Claude Desktop config file: **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` ```json { "mcpServers": { "markitdown": { "command": "markitdown-mcp", "env": { "PADDLE_API_URL": "your_api_url", "PADDLE_TOKEN": "your_token" } } } } ``` ## Links - [GitHub Repository](https://github.com/DuanYan007/markitdown) - [Issue Tracker](https://github.com/DuanYan007/markitdown/issues) ## License MIT License
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.