pdf-reader-mcp
by SylphxAI
Overview
Provides production-ready PDF processing capabilities for AI agents, including extraction of text, images, and metadata from local files or URLs.
Installation
npx @sylphx/pdf-reader-mcpEnvironment Variables
- DEBUG_MCP
Security Notes
The server explicitly supports reading PDFs from arbitrary absolute local file paths, meaning it can access any file on the host filesystem that the running process has permissions for. This poses a significant security risk if the AI agent's input is not rigorously controlled, as it could be exploited to read sensitive system files (e.g., /etc/passwd, .ssh keys) or other private data. While there's a 100MB size limit for PDFs to prevent memory exhaustion, the broad file access capability is a critical concern for general-purpose deployment. No 'eval' or obvious malicious patterns were found, and network requests are limited to specified URLs.
Similar Servers
kreuzberg
High-performance document intelligence platform for extracting text, metadata, and structured information (tables, images, chunks) from over 50 diverse document formats (PDFs, Office, images, HTML, etc.). It offers advanced OCR capabilities, multilingual support, and features like chunking, embeddings, and keyword extraction. Functionality is exposed via multiple language bindings and a Micro-service Communication Protocol (MCP) server for flexible integration.
kreuzberg
High-performance document intelligence for extracting text, metadata, and structured information from a wide range of document formats including PDFs, Office documents, images, and HTML. It supports advanced features like OCR, table extraction, chunking, language detection, and embedding generation, powered by a Rust core for native performance.
mcp-pdf-reader
Exposes local PDFs for reading, semantic search, chunking, and table extraction to MCP-compatible agents or via a CLI.
pdflens-mcp
Provides an MCP server for AI agents to programmatically read and extract information (text, page count, images) from PDF documents within user-defined workspaces.