# MinerU

> Use this tool when you need to extract data from various document formats, such as PDFs, images, DOCX, and PPTX, with support for OCR and batch processing. MinerU solves problems related to document parsing, data extraction, and information retrieval, making it ideal for use cases involving large volumes of documents. It accepts document files as input and outputs extracted data, providing a streamlined interface for automated document processing.

Canonical page: https://skillsregistry.net/skills/io-github-linxule-mineru  
JSON: https://api.skillsregistry.net/v1/skills/io-github-linxule-mineru

## Description

MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.

## Trust

- **Trust score (0–1):** 0.94
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.3
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-19

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.linxule%2Fmineru)
- **Repository:** <https://github.com/linxule/mineru-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "io-github-linxule-mineru"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-linxule-mineru` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-linxule-mineru/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt