A local-first MCP server that enables semantic search over PDF and DOCX documents using structure-aware parsing and vector storage. It allows users to query their local knowledge base through Claude Code without cloud dependencies or GPU requirements.
An MCP server that enables Claude Desktop or Claude Code to ingest and search local documents using vector embeddings, returning relevant chunks as tool results for the model to reason over.
A local MCP server that indexes and searches your Claude Code conversation history with both keyword and semantic search, fully private and running locally.
A local document search MCP server that indexes personal files and enables hybrid search (BM25 + semantic) for Claude to find and cite internal materials.