Add pdf2md-ai: AI-powered PDF to Markdown converter

[MANUJ243]

Summary

This PR adds pdf2md-ai, an MCP server that converts PDF files to Markdown using advanced AI (Gemini).

Server Details

• Name: pdf2md-ai
• Package: https://www.npmjs.com/package/pdf2md-ai
• Version: 1.0.0
• Transport: stdio (runs locally on user's machine)
• Dependencies: Node.js 18+
• Distribution: NPM package

Features

• AI-powered content extraction using Gemini
• Preserves document structure, tables, and formatting
• Credit-based SaaS model with free tier
• Fast processing with 5-minute timeout protection
• Multi-language support

Testing

The server has been tested successfully with:

• ✅ Claude Desktop (Windows & macOS config documented)
• ✅ VS Code with GitHub Copilot
• ✅ Various PDF types (invoices, contracts, reports, technical documents)

User Experience

Users install via NPX (no manual installation needed):

{
  "mcpServers": {
    "pdf2md-ai": {
      "command": "npx",
      "args": ["-y", "pdf2md-ai"],
      "env": {
        "PDF_TO_MARKDOWN_API_KEY": "their-key"
      }
    }
  }
}

Links
NPM Package: https://www.npmjs.com/package/pdf2md-ai
API Service: https://pdf-to-markdown-pro.onrender.com
Server Documentation: Included in README.md
Checklist
README.md includes clear installation instructions
README.md includes usage examples with expected output
Server is published and working on NPM
Server works with standard MCP clients (Claude Desktop, Cursor)
Documentation explains how to obtain API key
License is specified (MIT)
Use cases are clearly documented

[MANUJ243]

This is not just a simple PDF text extractor. pdf2md-ai preserves complete visual and structural context.

This means when you convert a technical PDF, a report with graphics, or documentation with code examples, you don't lose any visual or structural information.

[EPISTEX0]

Is it good for handling mathematical formulas? ex MathpixMarkdown, tks u

[cliffhall]

This is a reference server repo for educational purposes. We are not accepting unsolicited guide/doc additions, updates to our (now retired) community server list, Rating / badge / scoring for servers, Promotional "example" servers, or out of scope features. If you are trying to register a server, please go to https://registry.modelcontextprotocol.io