mcp-learning-memory
Verified Safeby nulone
Overview
Provides AI assistants with persistent, feedback-learning memory to save insights, track feedback, and improve information retrieval.
Installation
node dist/index.jsEnvironment Variables
- XDG_DATA_HOME
Security Notes
The server operates locally via standard I/O (stdio) and does not expose any network interfaces, significantly reducing external attack surface. It explicitly avoids `console.log` to prevent stdout pollution, which is critical for the MCP protocol. Robust input validation (`src/validation.ts`) prevents oversized or malformed data. Data integrity is prioritized with atomic file writes using a temp-file-and-rename pattern, mutex protection for concurrent access, and automatic recovery with backup generation for corrupted data files. No hardcoded secrets or 'eval' statements were found. The use of XDG Base Directory Specification for data storage is good practice.
Similar Servers
mcp-memory-service
A Model Context Protocol (MCP) server providing persistent, semantic memory storage and retrieval capabilities for AI agents. It supports lightweight semantic reasoning (contradiction, causal inference), content chunking, multi-backend storage (SQLite-vec, Cloudflare, Hybrid), autonomous memory consolidation (decay, association, clustering, compression, forgetting), and real-time updates via SSE. It's designed for token-efficient interaction with LLMs.
In-Memoria
Provides persistent intelligence infrastructure for AI agents, enabling them to understand codebases, detect patterns, predict coding approaches, and generate context-aware insights.
memory-graph
A graph-based MCP server that provides intelligent memory capabilities for Claude Code, enabling persistent knowledge tracking, relationship mapping, and contextual development assistance.
memory-mcp-server-go
A Model Context Protocol server providing knowledge graph management capabilities for LLMs to maintain memory across conversations.