"Pocket" matching MCP servers:

Enables AI assistants to save, retrieve, and manage research content using ChromaDB vector storage with semantic search, topic organization, and automatic deduplication powered by OpenAI embeddings.

A lightweight, local-first MCP server that automatically watches folders, chunks and embeds files using Transformers.js, and exposes semantic search capabilities to VS Code and Cursor. Runs completely offline with SQLite vector storage, designed for resource-constrained environments.