Pdf ReaderSAFE

A Model Context Protocol (MCP) server that provides tools for reading and extracting text from PDF files, supporting both local files and URLs.

Author

Philip Van de Walker Email: [email protected] GitHub: https://github.com/trafflux

Features

• Read text content from local PDF files
• Read text content from PDF URLs
• Error handling for corrupt or invalid PDFs
• Volume mounting for accessing local PDFs
• Auto-detection of PDF encoding
• Standardized JSON output format

Installation

1. Clone the repository:

git clone https://github.com/trafflux/pdf-reader-mcp.git
cd pdf-reader-mcp

1. Build the Docker image:

docker build -t mcp/pdf-reader .

Usage

Running the Server

To run the server with access to local PDF files:

docker run -i --rm -v /path/to/pdfs:/pdfs mcp/pdf-reader

Replace /path/to/pdfs with the actual path to your PDF files directory.

If not using local PDF files:

docker run -i --rm mcp/pdf-reader

MCP Configuration

Add to your MCP settings configuration:

{
"mcpServers": {
"pdf-reader": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-v",
"/path/to/pdfs:/pdfs",
"mcp/pdf-reader"
],
"disabled": false,
"autoApprove": []
}
}
}

Without local file PDF files:

{
"mcpServers": {
"pdf-reader": {
"command": "docker",
"args": ["run", "-i", "--rm", "mcp/pdf-reader"],
"disabled": false,
"autoApprove": []
}
}
}

Available Tools

1. read_local_pdf

• Purpose: Read text content from a local PDF file
• Input:

{
"path": "/pdfs/document.pdf"
}

• Output:

{
"success": true,
"data": {
"text": "Extracted content..."
}
}

1. read_pdf_url
2. Purpose: Read text content from a PDF URL
3. In