# Markdownify MCP — Convert Files and URLs to Markdown

> Markdownify MCP is an MCP server that converts PDFs, images, audio, and web pages into Markdown, with optional path allowlists for safer local file access.

## Install

Merge the JSON below into your `.mcp.json`:

## Quick Use

1. Clone + install dependencies:
   ```bash
   git clone https://github.com/zcaceres/markdownify-mcp.git
   cd markdownify-mcp
   bun install
   ```
2. Build + start:
   ```bash
   bun run build
   bun start
   ```
3. (Docker) Run with a read boundary:
   ```bash
   docker build -t markdownify-mcp .
   docker run --rm -i -v "$HOME/Documents:/data:ro" -e MD_ALLOWED_PATHS=/data markdownify-mcp
   ```

## Intro

Markdownify MCP is an MCP server that converts PDFs, images, audio, and web pages into Markdown, with optional path allowlists for safer local file access.

- **Best for:** agents that need document-to-Markdown ingestion (PDF/web/audio) before summarizing or indexing
- **Works with:** Bun/Node, optional Docker, optional `MD_ALLOWED_PATHS` allowlist
- **Setup time:** 15–30 minutes

## Practical Notes

- Data point: Docker mode can enforce a read boundary via `MD_ALLOWED_PATHS`.
- Quant: mount only one directory first (e.g. `/data`) to reduce accidental file exposure.

## Pattern: convert → then summarize

When an agent reads arbitrary documents, keep the pipeline explicit:
1) Convert to Markdown (normalize),
2) store the Markdown (cache),
3) summarize / chunk / index.

This avoids repeated parsing and makes outputs auditable.

## Security note

If your agent has local file access, always restrict paths (allowlist) and run conversion in a container when possible.

### FAQ

**Q: Does it support PDFs?**
A: Yes. The repo lists `pdf-to-markdown` and related tools.

**Q: How do I restrict what it can read?**
A: Set `MD_ALLOWED_PATHS` to an allowlist of directories.

**Q: Should I run it in Docker?**
A: If you’re exposing local files, Docker + read-only mounts is a safer default.

## Source & Thanks

> Source: https://github.com/zcaceres/markdownify-mcp
> License: MIT
> GitHub stars: 2,673 · forks: 223

---

<!-- ZH -->

## 快速使用

1. 克隆并安装依赖：
   ```bash
   git clone https://github.com/zcaceres/markdownify-mcp.git
   cd markdownify-mcp
   bun install
   ```
2. 构建并启动：
   ```bash
   bun run build
   bun start
   ```
3.（Docker）用“只读挂载 + 路径白名单”跑：
   ```bash
   docker build -t markdownify-mcp .
   docker run --rm -i -v "$HOME/Documents:/data:ro" -e MD_ALLOWED_PATHS=/data markdownify-mcp
   ```

## 简介

Markdownify MCP 是一个把 PDF/图片/音频/网页转换成 Markdown 的 MCP server，适合做 RAG/总结前的标准化处理，并支持用路径白名单限制本地文件读取范围。

- **适合谁：** 需要把文档（PDF/网页/音频）先转成 Markdown 再总结/索引的 agent
- **可搭配：** Bun/Node、可选 Docker、可选 `MD_ALLOWED_PATHS` 路径白名单
- **准备时间：** 15–30 分钟

## 实战建议

- 数据点：Docker 模式可用 `MD_ALLOWED_PATHS` 强制读取边界。
- 量化建议：先只挂载一个目录（例如 `/data`），减少误读文件的风险。

## 常用打法：先转换，再总结

让 agent 读各种文档时，建议把管线写清楚：
1）先转 Markdown（标准化），
2）保存 Markdown（缓存），
3）再做总结/切分/索引。

这样解析过程可审计、也避免反复解析。

## 安全提示

只要涉及本地文件读取，就要做路径限制（allowlist）；条件允许时用容器跑转换更稳。

### FAQ

**支持 PDF 吗？**
答：支持，仓库列出了 `pdf-to-markdown` 等工具。

**如何限制读取范围？**
答：设置 `MD_ALLOWED_PATHS` 只允许读取指定目录。

**需要用 Docker 吗？**
答：如果涉及本地文件，Docker + 只读挂载通常更安全。

## 来源与感谢

> Source: https://github.com/zcaceres/markdownify-mcp
> License: MIT
> GitHub stars: 2,673 · forks: 223


---
Source: https://tokrepo.com/en/workflows/markdownify-mcp-convert-files-and-urls-to-markdown
Author: MCP Hub