MIMICLab/mcp-pdf-vision
If you are the rightful owner of mcp-pdf-vision 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.
The MCP PDF Vision Server allows Claude to analyze PDF documents using its vision capabilities, providing a robust solution for handling complex PDF layouts and extracting valuable information.
Tools
Functions exposed to the LLM to take actions
load_pdf
Load a PDF file for analysis
get_current_page
Get the current page as an image
go_to_page
Navigate to a specific page
next_page
Navigate to the next page
previous_page
Navigate to the previous page
get_pages_range
Get multiple pages at once
get_all_pages
Get all pages from the PDF
get_pdf_info
Get information about the loaded PDF
list_sessions
List all active PDF sessions
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client