# MinerU

This MCP server sends PDFs, images, DOCX, and PPTX to MinerU for parsing, OCR, and batch jobs. Use it when an agent needs structured document output.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 10
- Author: linxule
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/linxule/mineru-mcp
- Updated: 2026-10-19
- HTML: https://affpapa.org/en/nevibecode/mcp/mineru

## What it does

MinerU exposes MinerU document-processing tools to an agent. It can parse a document URL, upload files from disk, handle several documents in one request, limit extraction to selected pages, and report task status. Results can be retrieved as Markdown with the original file names.

Long files can be split into page-range jobs and assembled from the available Markdown parts. The server also provides recorded operations, checkpoint continuation, cancellation of local processing, and bundle validation. Cloud actions need `MINERU_API_KEY`; offline bundle creation can run without credentials.

Local result retention, bundles, and recorded operations require macOS or Linux. On Windows, those filesystem paths fail closed. New setups should use Node.js 24; Node.js 18 or newer is supported as well.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add mineru -- npx -y mineru-mcp
```

### Codex

**Platform CLI**
```bash
codex mcp add mineru -- npx -y mineru-mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "mineru": {
            "command": "npx",
            "args": [
                "-y",
                "mineru-mcp"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "mineru": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "mineru-mcp"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add mineru npx -y mineru-mcp
```

## When to use it
- parse a PDF, DOCX, or PPTX from a URL
- send local files for batch processing
- extract Markdown from selected pages
- check a task and fetch its result
- split a long document and join its Markdown parts

## Example prompts
- Parse this PDF and return the extracted content as Markdown.
- Upload these local documents as one batch and keep their original file names in the results.
- Process this long document by page ranges, then combine the available Markdown slices.

## Similar
- [MinerU Open MCP](https://affpapa.org/en/nevibecode/mcp/mineru-open-mcp.md) — MCP server · ★ 230
- [pptx](https://affpapa.org/en/nevibecode/skills/pptx.md) — skill · 241433 installs
- [pdf](https://affpapa.org/en/nevibecode/skills/pdf.md) — skill · 216041 installs
- [cloudflare-email-service](https://affpapa.org/en/nevibecode/skills/cloudflare-email-service.md) — skill · 102300 installs
- [gws-shared](https://affpapa.org/en/nevibecode/skills/gws-shared.md) — skill · 66100 installs
- [gws-calendar](https://affpapa.org/en/nevibecode/skills/gws-calendar.md) — skill · 61200 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md