A Model Context Protocol server for converting documents to Markdown
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":"iflow-mcp-ww-ai-lab-any2markdown","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.
# Any2Markdown MCP 服务器 [](https://python.org) [](https://modelcontextprotocol.io/) [](LICENSE) []() 一个高性能的文档转换服务器,同时支持 **Model Context Protocol (MCP 模型上下文协议)** 和 **RESTful API** 接口。将 PDF、Word 和 Excel 文档转换为 Markdown 格式,具备图片提取、页眉页脚移除和批量处理等高级功能。 **📚 语言版本**: [English README](README-en.md) | [中文说明](README.md) ## ✨ 核心特性 ### 🔄 双协议支持 - **MCP 协议**:原生支持模型上下文协议和流式 HTTP 传输 - **RESTful API**:传统 HTTP API,配备 OpenAPI/Swagger 文档 - **统一后端**:两种协议共享相同的转换逻辑 ### 📄 文档转换 - **PDF 转 Markdown**:基于 [marker-pdf](https://github.com/VikParuchuri/marker) 的高质量文本提取 - **Word 转 Markdown**:支持 .docx/.doc 格式,保持格式化 - **Excel 转 Markdown**:支持 .xlsx/.xls 格式,表格转换 - **批量处理**:并发处理多个文档 ### 🖼️ 高级功能 - **图片提取**:从文档中提取图片并通过静态 URL 提供服务 - **页眉页脚移除**:智能移除重复的页面元素 - **多格式输出**:Markdown、HTML 和 JSON 输出格式 - **结构分析**:文档结构分析和验证 - **并发处理**:高性能异步处理和速率限制 ## 🚀 快速开始 ### 系统要求 - Python 3.9+ - 4GB+ 内存(用于 AI 模型) - 10GB+ 磁盘空间(用于模型缓存) ### 安装 ```bash # 克隆仓库 git clone https://github.com/WW-AI-Lab/any2markdown.git cd any2markdown # 创建虚拟环境 python -m venv .venv source .venv/bin/activate # Windows: .venv\Scripts\activate # 准备环境变量文件 cp env.example .env # 安装依赖 pip install -r requirements.txt ``` ### 快速启动 #### 方式一:Docker 部署(推荐,开箱即用) ```bash # 使用预构建镜像直接启动服务 docker run -d \ -p 3000:3000 \ --name any2markdown-mcp-server \ --restart unless-stopped \ -v $(pwd)/uploads:/app/uploads \ -v $(pwd)/temp_images:/app/temp_images \ -v $(pwd)/logs:/app/logs \ -v $(pwd)/models:/root/.cache/marker \ -v $(pwd)/models/huggingface:/root/.cache/huggingface \ -v $(pwd)/models/torch:/root/.cache/torch \ -v $(pwd)/models/transformers:/root/.cache/transformers \ ccr.ccs.tencentyun.com/yfgaia/any2markdown-mcp-server:latest # 💡 卷挂载说明: # - uploads/: 上传文件存储 # - temp_images/: 临时图片缓存…
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.