Vector Search

MCP Server for semantic text search in Milvus: converts natural language to vectors automatically, no manual vector input required.

Local-first, source-traceable agent memory — no LLM at ingest, fully offline

Minimal local RAG MCP server for document folders

MCP Server for micro-app knowledge base

Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.

Local MCP hub for personal data — private, cross-platform, agent-ready.

Memory Layer MCP for Claude Code — hybrid BM25 + vector search that compounds with usage (Korean ↔ English)

Local Memory Hub MCP Server with stdio transport for ZenCoder and MCP clients

Persistent graph memory MCP server for AI agents using LadybugDB

MCP tools for Memgraph graphs created by memgraph-ingester

MCP server for semantic search over markdown vaults

MCP server for Zotero — library tools + optional semantic search

Windows-optimized RAG MCP Server with Playwright crawling, Link Graph trees, and local hybrid search.

MCP server for Weaviate vector database operations

A neural network-powered security middleware and reverse proxy for the Model Context Protocol (MCP). Detects tool poisoning, shadowing, and prompt injection attacks using deep learning classifiers trained on SentenceTransformer embeddings.

MCP server for cloud-based vector code search

CLI-first semantic code search with MCP integration and interactive D3.js visualization for exploring code relationships

Self-hosted local file indexing MCP server with semantic search

Semantically filter MCP tool catalogs to cut LLM input-token costs. Ships with AWS Bedrock defaults; bring-your-own provider supported.

Local long-term memory for Claude Code and other agents: every message kept word for word, no cloud.