Marktechpost AI team released Token Saver, an open-source Model Context Protocol (MCP) extension for Claude Desktop (MIT licensed, currently at v1.0), developed at Marktechpost AI Media Inc by Arnav Rai, a CS student at Rochester Institute of Technology, during his internship supervised by Jean-marc Mommessin and Asif Razzaq. The tool addresses the hidden cost of context windows when analyzing large documents with LLMs, as conversation history is re-sent to the model on every turn. Token Saver implements a Local Hybrid RAG system directly on the user's machine, allowing questions about massive PDFs without uploading the file to the model. Token consumption is slashed by 92% to 99%, privacy is guaranteed, and setup requires zero Python environments or terminal configurations. Claude’s default behavior converts each PDF page into an image while separately extracting text, with text alone running 1,500 to 3,000 tokens per page. Token Saver acts as a local MCP server, combining Keyword Matching (BM25) over SQLite’s FTS5 search (weighted at 0.4) and Semantic Search using a local all-MiniLM-L6-v2 embedding model (weighted at 0.6). The server searches the file and hands Claude only relevant passages, which then synthesizes answers, citing exact page numbers and providing a running tally of saved tokens. The pipeline executes eight rapid steps inside a single local