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_pdf2md convert this 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 for AI-optimized PDF to Markdown conversion using pdf2md.
Requires pi-mcp-bridge to connect to pi.
pdf2md CLI installed (cargo install pdf2md or brew install pdf2md)
Related MCP server: PDF MCP Flow
npm install -g timaliev/mcp_pdf2md
# or
git clone https://github.com/timaliev/mcp_pdf2md.git
cd mcp_pdf2md && npm linkIn ~/.pi/agent/settings.json:
{
"mcpBridge": {
"servers": [
{
"name": "pdf2md",
"command": "mcp-pdf2md",
"args": []
}
]
}
}In ~/.mcp.json:
{
"mcpServers": {
"pdf2md": {
"command": "mcp-pdf2md",
"args": []
}
}
}Tool | Description |
| Convert PDF to Markdown with page range, raw/compact/page-break options |
| Detect PDF type: TextBased, Scanned, Mixed, ImageBased |
git clone https://github.com/timaliev/mcp_pdf2md.git
cd mcp_pdf2md
npm installThis server cannot be deployed
High-fidelity PDF to structured Markdown conversion and document field extraction.
Convert documents and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scanned files, any URL.
Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.
Convert PDF, DOCX, HTML, and URLs to clean, LLM-ready markdown with tables preserved
