Mcp Markitdown Base
What is Mcp Markitdown Base
mcp-markitdown-base is an MCP (Multi-Agent Communication Protocol) service based on the MarkItDown library, designed to convert various file formats into Markdown text.
Use cases
Use cases include converting academic papers from PDF to Markdown for easier editing, transforming PowerPoint presentations into Markdown for web publishing, and extracting text from images or audio files for documentation purposes.
How to use
To use mcp-markitdown-base, clone the repository and utilize the convertFileToMarkdown tool through an MCP client. Provide the file path and an optional result path for saving the converted Markdown text.
Key features
Key features include the ability to convert a wide range of file formats such as PDF, PowerPoint, Word, Excel, images (with EXIF metadata and OCR), audio (with EXIF metadata and speech transcription), HTML, text-based formats (CSV, JSON, XML), ZIP files, YouTube URLs, and EPubs. The service also allows saving the converted Markdown text to a specified path.
Where to use
mcp-markitdown-base can be used in various fields such as document management, content creation, educational resources, and any application requiring file format conversions to Markdown.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Mcp Markitdown Base
mcp-markitdown-base is an MCP (Multi-Agent Communication Protocol) service based on the MarkItDown library, designed to convert various file formats into Markdown text.
Use cases
Use cases include converting academic papers from PDF to Markdown for easier editing, transforming PowerPoint presentations into Markdown for web publishing, and extracting text from images or audio files for documentation purposes.
How to use
To use mcp-markitdown-base, clone the repository and utilize the convertFileToMarkdown tool through an MCP client. Provide the file path and an optional result path for saving the converted Markdown text.
Key features
Key features include the ability to convert a wide range of file formats such as PDF, PowerPoint, Word, Excel, images (with EXIF metadata and OCR), audio (with EXIF metadata and speech transcription), HTML, text-based formats (CSV, JSON, XML), ZIP files, YouTube URLs, and EPubs. The service also allows saving the converted Markdown text to a specified path.
Where to use
mcp-markitdown-base can be used in various fields such as document management, content creation, educational resources, and any application requiring file format conversions to Markdown.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
MCP MarkitDown Base
这是一个基于 MarkItDown 库的 MCP (Multi-Agent Communication Protocol) 服务，用于将各种文件格式转换为 Markdown 文本。
功能
- 将指定文件转换为 Markdown 格式的文本。
- 支持多种文件格式，包括 PDF、PowerPoint、Word、Excel、Images (EXIF metadata and OCR)、Audio (EXIF metadata and speech transcription)、HTML、Text-based formats (CSV, JSON, XML)、ZIP files (iterates over contents)、Youtube URLs、EPubs。
- 可选择将转换后的 Markdown 文本保存到指定路径。
安装
-
克隆仓库：
git clone https://gitee.com/mcp-markitdown-base.git
使用
该服务通过 MCP 协议提供 convertFileToMarkdown 工具。您可以通过 MCP 客户端调用此工具。
convertFileToMarkdown 工具
- 描述：根据传入的文件路径，将文件转换为 markdown 格式，并返回转换后的 markdown 文本。
- 参数：
file(str): 文件路径，根据系统写绝对路径。resultPath(str): 转换后的 markdown 文本保存路径，默认传入空字符串""即可。如果明确要求路径则根据系统写绝对路径。
示例 (通过 MCP 客户端调用)
MCP 客户端配置示例(Windows)
以下是一个 MCP 客户端的配置示例，用于启动此服务：
{
"mcpServers": {
"mcp-markitdown-base": {
"command": "uv",
"args": [
"run",
"--directory",
"E:\\mcp-markitdown-base",
"main.py"
]
}
}
}请将 E:\\mcp-markitdown-base 替换为您的项目实际路径，并确保路径中的反斜杠 \ 已正确转义为 \\。
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
