ContextKeep
Verified Safeby mordang7
Overview
ContextKeep provides a standalone memory server for AI agents to store and retrieve long-term conversational context, project details, and code snippets, reducing LLM token usage.
Installation
python server.pySecurity Notes
The server and web UI default to binding on '0.0.0.0' (all network interfaces) on ports 5100 and 5000 respectively, making them accessible from the local network by default. While this enables features like remote SSH access, users should be aware that these services are network-exposed, which could be a privacy or security concern if not intended or if the host machine is not adequately secured. Memory keys used for filenames are sanitized via MD5 hashing, mitigating direct path traversal vulnerabilities. The installation scripts use standard system commands and `sudo`, which require careful review but do not show obvious direct command injection vulnerabilities from user input.
Similar Servers
mcp-memory-service
A comprehensive, AI-enhanced memory service for AI agents, enabling semantic search, intelligent consolidation, and multi-backend storage via a token-efficient API and MCP protocol.
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 for AI agents.
mcp-duckdb-memory-server
Serves as a local knowledge graph memory backend for LLMs, storing entities, relations, and observations using DuckDB for efficient querying and data management.
context-sync
Providing persistent memory and context synchronization for AI development across various tools and projects.