mcp-server-convert
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., "@mcp-server-convertconvert the file /home/user/report.pdf to 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.
mcp-server-convert
A lightweight Model Context Protocol (MCP) server that converts documents to Markdown. Supports PDF, DOCX, HTML, EPUB, CSV, JSON, and plain text files.
Perfect for AI agents that need to ingest and understand document content.
Features
📄 Multi-format support: PDF, DOCX, HTML, EPUB, CSV, JSON, images (via OCR), and plain text
🔧 6 MCP tools:
convert_file,convert_url,list_supported_formats,batch_convert,extract_metadata,convert_directory🐍 Zero external dependencies for core: Uses Python standard library +
markdownifyfor HTML⚡ Fast: In-memory processing, no temp files
🐳 Docker-ready: Single Dockerfile, one command deploy
Related MCP server: Unstructured Document Processor MCP
Quick Start
Install & Run
# Clone
git clone https://github.com/demo112/mcp-server-convert.git
cd mcp-server-convert
# Install dependencies
pip install -r requirements.txt
# Run
python -m mcp_server_convertConfigure in Claude Code
Add to your MCP settings (~/.claude/settings.json):
{
"mcpServers": {
"convert": {
"command": "python",
"args": ["-m", "mcp_server_convert"],
"cwd": "/path/to/mcp-server-convert"
}
}
}Docker
docker build -t mcp-server-convert .
docker run -i --rm mcp-server-convertConfigure with Docker
{
"mcpServers": {
"convert": {
"command": "docker",
"args": ["run", "-i", "--rm", "-v", "/path/to/files:/data", "mcp-server-convert"]
}
}
}Tools
convert_file
Convert a local file to Markdown.
Parameters:
file_path(string, required): Absolute path to the filemax_length(int, optional): Maximum output length in chars (default: 50000)
convert_url
Fetch a URL and convert its content to Markdown.
Parameters:
url(string, required): URL to fetch and convertmax_length(int, optional): Maximum output length in chars (default: 50000)
batch_convert
Convert multiple files at once.
Parameters:
file_paths(array of strings, required): List of file pathsmax_length_per_file(int, optional): Max length per file (default: 50000)
convert_directory
Convert all supported files in a directory.
Parameters:
dir_path(string, required): Path to directoryrecursive(bool, optional): Include subdirectories (default: true)max_files(int, optional): Maximum files to convert (default: 20)
extract_metadata
Extract metadata from a file without full conversion.
Parameters:
file_path(string, required): Path to the file
list_supported_formats
List all supported file extensions and their conversion methods.
Supported Formats
Format | Extension | Method |
| PyMuPDF (fitz) | |
Word |
| python-docx |
HTML |
| markdownify |
EPUB |
| ebooklib |
CSV |
| pandas → markdown table |
JSON |
| Formatted markdown code block |
XML |
| xmltodict → markdown |
Excel |
| openpyxl → markdown table |
PowerPoint |
| python-pptx → markdown slides |
Text |
| Direct passthrough |
Images |
| pytesseract OCR (if available) |
Support
If this tool helps your workflow, consider supporting its development:
GitHub Sponsors: Sponsor via Liberapay
ETH:
0xddD9f45e14c92846f47C1c1A4431aC2b41D87273
License
MIT
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.
Convert PDF, Word, PowerPoint, Excel, HTML and EPUB to Markdown, with OCR and RAG chunking
Convert documents and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scanned files, any URL.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA server that provides document processing capabilities using the Model Context Protocol, allowing conversion of documents to markdown, extraction of tables, and processing of document images.19MIT
- FlicenseBqualityDmaintenanceA Model Context Protocol server that enables LLMs to extract and use content from unstructured documents across a wide variety of file formats.111-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that converts various file formats (PDF, PowerPoint, Word, Excel, Images, etc.) to Markdown to make them accessible to LLMs.1MIT
- AlicenseAqualityAmaintenanceA Model Context Protocol server that converts over 29 file formats, including PDFs, Office documents, and audio, into structured Markdown using Microsoft's MarkItDown library. It enables AI assistants to process diverse document types through single file conversion and batch directory processing.375 PyPI33MIT