PDF Agent MCP

{ "dxt_version": "0.1", "name": "pdf-agent-mcp", "version": "0.0.2", "display_name": "PDF Agent MCP", "description": "A Model Context Protocol server designed for agentic reading and selective PDF processing, enabling AI systems to efficiently navigate and extract content without context window limitations.", "long_description": "This extension enables AI agents like Claude to read and search PDFs intelligently, just like humans do. Instead of processing entire documents, this tool allows agents to extract specific sections, analyze table of contents for navigation, perform targeted text extraction, and process images with OCR only when needed. Perfect for research, document analysis, and searching through multiple large documents.", "author": { "name": "Vlad Gheorghe", "url": "https://github.com/vlad-ds" }, "license": "ISC", "keywords": ["pdf", "document", "extraction", "analysis", "ocr", "toc", "table-of-contents"], "icon": "icon.png", "tools": [ { "name": "get_pdf_metadata", "description": "Extract metadata and basic information from a PDF file, including page count, file size, creation dates, and document properties" }, { "name": "get_pdf_text", "description": "Extract text from specific pages or page ranges of a PDF file using hybrid extraction. Supports enhanced page ranges including comma-separated combinations (e.g., '1,3:5,7')" }, { "name": "get_pdf_images", "description": "Extract specific pages or page ranges from a PDF as images for visual analysis. Supports enhanced page ranges including comma-separated combinations (e.g., '1,3:5,7'). Essential for charts, diagrams, tables, figures, equations, and visual content that text cannot capture" }, { "name": "search_pdf", "description": "Search for text patterns (including regex) within a PDF file and return matching pages with context snippets. Supports enhanced page ranges including comma-separated combinations (e.g., '1,3:5,7')" }, { "name": "get_pdf_outline", "description": "Extract the table of contents (TOC) or outline/bookmarks structure from a PDF file with hierarchical navigation structure" }, { "name": "download_pdf", "description": "Download a PDF from a URL and save it to the PDF agent home directory, returning the full path of the downloaded PDF" }, { "name": "search_multiple_pdfs", "description": "Search for text patterns across multiple PDF files in parallel. For large batches of files, prefer a single call with high parallelism rather than multiple smaller calls (e.g., search 100 files with parallelism=50 in one call instead of multiple calls with 20 files each)" } ], "server": { "type": "node", "entry_point": "server/index.js", "mcp_config": { "command": "node", "args": ["${__dirname}/server/index.js"] } }, "compatibility": { "platforms": ["darwin", "win32", "linux"], "runtimes": { "node": ">=16.0.0" } } }