patriciomartinns/pdf-toolbox
If you are the rightful owner of pdf-toolbox and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
The MCP PDF Reader is a tool designed to expose local PDFs to MCP-compatible agents, offering features like deterministic chunking, semantic embeddings, and reproducible ingestion pipelines.
Tools
Functions exposed to the LLM to take actions
read_pdf
Extract ordered text for a bounded page range (default max 25 pages).
search_pdf
Run semantic similarity over cached embeddings and return ranked hits.
describe_pdf_sections
Generate deterministic chunks with offsets for downstream ingestion.
configure_pdf_defaults
Update runtime defaults for pagination, chunking, and the embedding model.
Prompts
Interactive templates invoked by user choice
No prompts
Resources
Contextual data attached and managed by the client