Provides a lightweight, local-first server for semantic search, file chunking, and embeddings with a web UI and API.
Sponsored
PocketMCP is a lightweight, local-first MCP (Model Context Protocol) server that automatically watches folders, chunks and embeds files locally using Transformers.js with MiniLM, stores vectors in SQLite + sqlite-vec, and exposes semantic search capabilities to VS Code and Cursor. Designed for small machines (I'm running on an Intel N100 with 16GB RAM) with zero external dependencies after initial model download.
主要功能
01Automated file ingestion and processing for multiple formats (PDF, DOCX, Markdown, text).
02Semantic search for content by meaning, not just keywords.
03Built-in web interface and API for testing, validation, and manual document management.
04Native MCP integration for VS Code and Cursor, supporting both stdio and HTTP transports.
050 GitHub stars
06Local-first operation with offline capabilities and efficient SQLite vector storage.
使用案例
01Providing a self-hosted, resource-efficient semantic search backend for custom web or desktop applications.
02Enhancing AI coding assistants (VS Code, Cursor) with local-first semantic search capabilities.
03Building personal or team-specific knowledge bases from various document types for rapid content retrieval.
