pdf-reader-mcp
24
The PDF Reader MCP Server is a tool designed to assist AI agents in securely reading and extracting information from PDF files, such as text and metadata. The server prioritizes security and efficiency, providing structured outputs for easy AI integration.
How do I install the PDF Reader MCP Server?
You can install it using npm with pnpm add @sylphlab/pdf-reader-mcp or pull the Docker image with docker pull sylphlab/pdf-reader-mcp:latest.
What kind of PDF data can be extracted?
The server can extract full text, specific page text, metadata, and page count from PDF files.
Is the server secure?
Yes, it confines file access strictly to the project root directory, ensuring secure operations.
Can it handle multiple PDF files in one request?
Yes, it can process multiple PDF sources, whether local paths or URLs, in a single request.
What libraries does the server use for parsing?
The server uses pdfjs-dist for parsing and Zod for input validation.