How do I deploy markitdown-mcp-rest on Railway?

You can deploy markitdown-mcp-rest on Railway by clicking the "Deploy Now" button on this page. Railway will automatically set up all the necessary services and configurations for you.

What are the system requirements?

Railway handles all the infrastructure requirements. You only need a web browser to deploy and manage your application.

Is this template free to use?

Yes, this template is free to use within your existing Railway account.

Can I customize this template?

Yes, you can fully customize this template. After deployment, you will have full control of what you've deployed in your Railway project.

How do I get support for this template?

You can get support through our community forum: markitdown-mcp-rest-cefb6481, or click "Get template help" for this template for more assistance.

Deploy and Host markitdown-mcp-rest on Railway

MarkItDown MCP + REST is a self-hosted document conversion service built on Microsoft's MarkItDown library. It converts PDF, Word, Excel, PowerPoint, HTML, images, audio, and more into clean Markdown via a REST API or MCP (Model Context Protocol) server -- ready for LLM pipelines, RAG systems, and text analysis workflows.

About Hosting markitdown-mcp-rest

Hosting markitdown-mcp-rest on Railway gives you a production-ready document-to-Markdown conversion service with zero infrastructure management. The template deploys a Docker container with the FastAPI REST API, which accepts file uploads or URIs and returns structured Markdown. It includes Bearer token authentication (auto-generated on deploy), a health check endpoint for zero-downtime deploys, and built-in support for all major document formats. The same image can also run the MCP server for direct integration with LLM applications like Claude Desktop, Cursor, and other MCP-compatible clients.

Common Use Cases

LLM document ingestion -- Convert uploaded documents to Markdown for RAG pipelines, embeddings, and context windows
MCP tool for AI assistants -- Give Claude, Cursor, or any MCP client the ability to read and convert files on demand
Automated document processing -- Build workflows that convert incoming PDFs, spreadsheets, and presentations into structured Markdown for indexing or analysis

Dependencies for markitdown-mcp-rest Hosting

Python 3.13 -- Runtime environment
FastAPI + Uvicorn -- REST API framework and ASGI server
markitdown[all] -- Core conversion library with support for PDF, DOCX, PPTX, XLSX, HTML, images, audio, and more
markitdown-mcp -- MCP server exposing convert_to_markdown over Streamable HTTP and SSE
ffmpeg -- Audio and video file metadata extraction
exiftool -- Image EXIF metadata extraction

Deployment Dependencies

Microsoft MarkItDown -- Core library documentation and supported formats
Model Context Protocol -- MCP specification for LLM tool integration
FastAPI -- REST API framework documentation

Implementation Details

The REST API exposes two conversion endpoints, both protected by Bearer token authentication. Convert a URI by sending a POST to /convert with a JSON body containing the URI. Upload a file by sending a POST to /convert/file with a multipart form. Both return structured JSON with the converted Markdown and document title. Interactive API documentation is available at the /docs endpoint (Swagger UI).

Why Deploy markitdown-mcp-rest on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying markitdown-mcp-rest on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.