mcp-markitdown-base

# MCP MarkitDown Base This is an MCP (Multi-Agent Communication Protocol) service based on the `MarkItDown` library, designed to convert various file formats into Markdown text. ## Features - Converts specified files into Markdown format text. - Supports multiple file formats, including 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, and EPubs. - Optionally saves the converted Markdown text to a specified path. ## Installation 1. Clone the repository: ```bash git clone https://gitee.com/mcp-markitdown-base.git ``` ## Usage The service provides the `convertFileToMarkdown` tool via the MCP protocol. You can call this tool through the MCP client. ### `convertFileToMarkdown` Tool - **Description**: Converts the file at the given file path into Markdown format and returns the converted Markdown text. - **Parameters**: - `file` (str): File path, write the absolute path according to the system. - `resultPath` (str): Path to save the converted Markdown text, you can pass an empty string `""` by default. If a specific path is required, write the absolute path according to the system. ### Example (Calling via MCP Client) MCP client configuration example (Windows) Here is an example configuration for an MCP client to start this service: ```json { "mcpServers": { "mcp-markitdown-base": { "command": "uv", "args": [ "run", "--directory", "E:\\mcp-markitdown-base", "main.py" ] } } } ``` Please replace `E:\\mcp-markitdown-base` with the actual path of your project, and ensure that the backslashes `\` in the path are correctly escaped as `\\`.