nocturne_memory
Verified Safeby Dataojitori
Overview
Provides a Neo4j-based long-term memory and dynamic knowledge graph system for AI agents, facilitating human collaboration, structured memory storage, and rollback capabilities.
Installation
python path/to/nocturne_memory/backend/mcp_server.pyEnvironment Variables
- NEO4J_URI
- dbuser
- dbpassword
- PORT
- HOST
Security Notes
The FastAPI backend (accessible by the frontend and potentially directly) uses `allow_origins=["*"]` for CORS, which is explicitly noted as for development but poses a significant security risk if deployed in production without restrictions. The provided backend code lacks explicit authentication and authorization mechanisms for its API endpoints. This means any client able to reach the API (e.g., via the frontend or directly) could perform operations like creating, updating, or deleting nodes/relationships. However, Neo4j queries are parameterized, mitigating Cypher injection risks, and database credentials are loaded from environment variables, preventing hardcoded secrets. The core MCP server component is typically run locally or in a trusted, isolated environment with AI agents.
Similar Servers
mcp-neo4j
The MCP Neo4j Cypher server enables AI models to interact with a Neo4j graph database, execute Cypher queries (read and write), explore the graph schema, and manage query performance and response sizes.
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
Provides a persistent knowledge graph server for LLMs to manage and retrieve entities, relations, and observations, acting as long-term memory across conversations.
post-cortex
Provides long-term, persistent memory and knowledge management for AI assistants, enabling them to store, semantically search, and retrieve conversation context, decisions, and code-related insights.