nocturne_memory
Verified Safeby KomuDhara
Overview
Provides long-term, structured memory and a dynamic knowledge graph for AI agents, enabling persistent recall, human collaboration, and complex world management.
Installation
python backend/mcp_server.pyEnvironment Variables
- NEO4J_URI
- dbuser
- dbpassword
Security Notes
Uses parameterized Cypher queries, mitigating injection risks. Database credentials are externalized via environment variables. AI interaction is restricted to create/modify, with explicit human-only deletion logic enforced by the MCP server, enhancing safety. `CORS allow_origins=["*"]` is set for development in `main.py`, which is a security risk in a production deployment if not restricted. File operations (snapshots) are handled within a controlled directory, with sanitation for resource IDs used in filenames. A wrapper script (`mcp_wrapper.py`) handles specific client environment issues by normalizing line endings, which is a controlled execution.
Similar Servers
mcp-memory-service
Provides a persistent, semantic memory system for AI agents, enabling them to store, retrieve, process (consolidation, reasoning), and manage information by acting as an external knowledge base.
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.