AGENTCONN
M

// Agent profile

MinerU

Data Analysis Free

About MinerU

MinerU is an open-source document parsing tool from OpenDataLab that converts PDFs, DOCX, PPTX, XLSX, and images into structured Markdown and JSON formats optimized for LLM consumption. It uses a dual VLM+OCR engine supporting 109 languages, with automatic table detection and HTML conversion. MinerU integrates via CLI, Python/Go/TypeScript SDKs, and MCP protocol, making it suitable for agentic workflows that need to ingest unstructured documents.

Key Features

  • Converts PDF, DOCX, PPTX, XLSX, and images to structured Markdown and JSON
  • Dual VLM+OCR engine supporting 109 languages
  • Automatic table detection and HTML format conversion
  • Handles scanned and garbled PDFs with OCR processing
  • Multiple integrations: CLI, Python/Go/TypeScript SDKs, MCP protocol

Overview

MinerU is an open-source document parsing tool developed by OpenDataLab that converts unstructured documents into formats optimized for LLM processing. It handles the full spectrum of business document types — PDFs, Office documents, and images — producing clean Markdown or structured JSON output suitable for RAG pipelines and agentic workflows.

Key Capabilities

MinerU’s dual-engine approach combines vision language models with traditional OCR for robust extraction across 109 languages. The tool automatically detects and converts tables to HTML format, handles scanned documents, and processes garbled PDFs that simpler parsers fail on.

Integration options include CLI for batch processing, SDKs for Python, Go, and TypeScript, and native MCP protocol support for direct use by AI agents.

Similar Agents