lizTheDeveloper/pdf-indexer-mcp

3.2

If you are the rightful owner of pdf-indexer-mcp 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 PDF Indexer MCP Server is a Model Context Protocol server that allows AI agents to download, index, and semantically search PDF research papers using a suite of tools.

Tools

Functions exposed to the LLM to take actions

download_pdf

Downloads a PDF research paper from a URL and saves it locally.

chunk_pdf

Extracts text from a PDF and chunks it using header-based or S2 chunking.

index_pdf

Complete indexing workflow - downloads, chunks, and stores in database.

list_indexed_papers

Lists all papers currently indexed in the database.

get_document_structure

Gets the complete structure of a paper (sections, headers, chunk ranges).

get_document_section

Retrieves a specific section of a document.

generate_embeddings

Generates semantic embeddings for all chunks in a paper and adds them to the FAISS vector index.

search_research_papers

Semantically searches all indexed papers using embeddings and returns the most relevant chunks.