mcp-pdf-reader

a3tai/mcp-pdf-reader

3.2

If you are the rightful owner of mcp-pdf-reader and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

MCP PDF Reader is an open source Model Context Protocol (MCP) server designed for reading and analyzing PDF documents, enabling seamless interaction with PDF files through a standardized protocol.

Tools

Functions exposed to the LLM to take actions

pdf_read_file

Extract text content from a PDF file.

pdf_assets_file

Extract visual assets like images from a PDF file.

pdf_validate_file

Validate if a file is a readable PDF.

pdf_stats_file

Get detailed statistics about a PDF file including metadata.

pdf_search_directory

List and search PDF files in a directory with optional fuzzy search.

pdf_stats_directory

Get statistics about PDF files in a directory.

pdf_extract_structured

Extract structured content with positioning coordinates and formatting information.

pdf_extract_tables

Extract tabular data from PDF with structure preservation and cell-level analysis.

pdf_extract_semantic

Extract content with semantic grouping and relationship detection.

pdf_extract_complete

Comprehensive extraction of all content types (text, images, tables, forms, annotations).

pdf_query_content

Query and filter extracted PDF content using flexible search criteria.

pdf_get_page_info

Get detailed information about PDF pages including dimensions, layout, and properties.

pdf_get_metadata

Extract comprehensive document metadata and properties.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources