read_pdf
Extract text per page from a PDF.
How to use it
read_pdf is exposed by the Academia MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the read_pdf tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
FULL ACADEMIA MCP LISTINGOther tools in Academia MCP (14)
Search ACL Anthology with fielded queries and optional date filtering.
Fetch a paper by ID and convert to structured text (HTML/PDF modes).
Query arXiv with field-specific queries and filters.
Compile LaTeX to PDF in WORKSPACEDIR.
Answer questions over provided document chunks (requires LLM).
, reviewpdfpaper: Download and optionally review PDFs (requires LLM + workspace).
, bravewebsearch, tavilywebsearch: Provider-specific search.
, generateresearchproposals, scoreresearchproposals: Research proposal helpers (requires LLM).
, getlatextemplate: Enumerate and fetch built-in LaTeX templates.
Find Hugging Face datasets with filters and sorting.
List papers citing a given arXiv paper (Semantic Scholar Graph).
List papers referenced by a given arXiv paper.
Fetch and normalize a web page.
Unified search wrapper; available when at least one of Exa/Brave/Tavily keys is set.