Local AI use cases with MCP
The Model Context Protocol is an open standard for exposing tools and data to AI agents. Local projects use it to let agents query notes, documents or databases.
Offline RAG over 268 Obsidian notes, queryable from a coding agent
nomic-embed-text, ChromaDB and mistral-nemo:12b give cited answers from a vault of internal docs, and an MCP server lets the coding agent search it too.
Receipt extraction and bank matching with PaperCortex
An open-source local AI layer for Paperless-ngx. It answers plain-English questions, extracts receipt line items, matches bank transactions and exports to DATEV.