mineru-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mineru-mcpparse the file report.pdf into markdown"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MinerU MCP Server
安装
uv syncRelated MCP server: PDF2MD MCP Server
pip
uv pip install -U "mineru[all]"MCP 配置
# reasonix
[[plugins]]
name = "mineru"
command = "python"
args = ["path/to/mineru-env/server.py"]
auto_start = true// Claude Desktop / Cline / 通用 MCP 客户端
{
"mcpServers": {
"mineru": {
"command": "python",
"args": ["path/to/mineru-env/server.py"]
}
}
}注意:
command需指向 mineru 所在 venv 的 python(如path/to/.venv/bin/python),确保能 importmcp和找到mineru二进制。
AI Tool 使用指南
本 MCP 提供两个 tool。
mineru_parse — 解析文档
将 PDF/图片/Office 文档解析为 Markdown。参数透传 mineru CLI,默认 --backend vlm-engine --effort high,无需重复传入。
// 最简调用
["-p", "/path/to/doc.pdf", "-o", "/tmp/output"]
// 指定页码范围
["-p", "/path/to/doc.pdf", "-o", "/tmp/output", "-s", "0", "-e", "10"]
// 批量解析目录
["-p", "/path/to/pdf_dir", "-o", "/tmp/output"]
// 查看帮助
["--help"]mineru_read_result — 读取已有结果
从之前的输出目录重读解析结果,避免重复解析。
{ "result_dir": "/tmp/output" }This server cannot be deployed
Maintenance
Related MCP Connectors
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
Related MCP Servers
- AlicenseAqualityFmaintenanceAn MCP server that exports PDF documents to markdown format optimized for LLM processing.11BSD 3-Clause
- AlicenseAqualityDmaintenanceAn MCP server that converts PDF files to Markdown format using AI sampling capabilities, supporting both local files and URLs with incremental conversion features.11MIT
- AlicenseAqualityCmaintenanceOfficial MinerU MCP server for parsing PDF, DOCX, PPTX, images, and HTML into Markdown. Supports 109-language OCR, Flash mode (no token), and Precision mode (token)2206Apache 2.0

pymupdf4llm-mcpofficial
AlicenseNot gradedqualityBmaintenanceMCP server for exporting PDF to markdown, optimized for LLM consumption.1,982 PyPI71AGPL 3.0