Awesome MCP › Other MCP Servers

sylphxltd/pdf-reader-mcp

⭐ 924 TypeScript added to this list on 2025-10-21 repository created 2025-04-04

The project "pdf-reader-mcp" by sylphxltd is an MCP (Model Context Protocol) server designed to empower AI agents with the ability to securely read and extract information from PDF files. Built with Node.js and TypeScript, it leverages the pdf-parse library and pdfjs-dist for reliable PDF parsing. The server can handle both local PDF files and PDFs accessible via URLs, providing a flexible and secure tool for extracting text, metadata, and page counts from PDFs within a project context. The server is designed to be integrated easily into MCP environments, supporting installation via npm or Docker. It can be configured to run as a local build for development purposes. The MCP host can invoke the server using commands like npx or Docker run, ensuring seamless integration into AI workflows. Key features include the ability to read full text content, extract text from specific pages or page ranges, retrieve PDF metadata such as author and creation date, and obtain the total page count. The server processes multiple PDF sources in a single request and confines file access strictly to the project root directory to ensure security. The output is structured in a predictable JSON format, making it easy for AI agents to parse and utilize the extracted data. The project emphasizes security, flexibility, and robustness, using Zod for input validation and providing performance benchmarks that demonstrate efficient handling of various PDF operations. The design philosophy focuses on minimal dependencies, security through context confinement, and efficiency via structured data transfer. Compared to other solutions like direct file access or external CLI tools, this MCP server offers a secure, integrated interface tailored for AI agents. Future plans include enhancing documentation, expanding benchmarking, optimizing for large PDFs, exploring image and annotation extraction, and increasing test coverage. The project is open source under the MIT License and encourages community contributions and feedback.

https://github.com/sylphxltd/pdf-reader-mcp

ai-agentai-agentsai-integrationdockerjson-outputllm-toollocal-and-url-pdf-sourcesmcpmcp-servermetadata-extractionmit-licensemodel-content-protocolnode.jsnodejsnpmopen-sourcepage-countpdfpdf-parsepdf-parserpdf-readerpdfjs-distperformance-benchmarksproject-root-confinementsecure-file-accessstdiostructured-datatext-extractiontypescriptzod-validation