claude-memory-server
Verified Safeby emmilco
Overview
Persistent memory and documentation search for AI agents, specifically for code understanding, indexing, and retrieval (RAG).
Installation
python -m src.mcp_serverEnvironment Variables
- QDRANT_URL
- QDRANT_API_KEY
- EMBEDDING_MODEL
- LOG_LEVEL
- PROJECT_NAME
- DATA_DIR
- EMBEDDING_CACHE_ENABLED
- EMBEDDING_CACHE_PATH
- EMBEDDING_CACHE_TTL_DAYS
- FORCE_CPU
- GPU_ENABLED
- GPU_MEMORY_FRACTION
- PARALLEL_WORKERS
Security Notes
The server demonstrates a strong focus on security with explicit input validation (`src/core/validation.py`) to detect and prevent SQL, command, and path traversal injections. It includes a dedicated security logger (`src/core/security_logger.py`) for auditing suspicious activities. The dashboard (`src/dashboard/web_server.py`), while setting 'Access-Control-Allow-Origin: *', is designed for local-only use (defaults to localhost:8080), mitigating this risk if not exposed externally. Usage of `subprocess` is primarily for CLI tools and Git operations, which is common for developer tools and appears to be handled with care. No obvious hardcoded secrets were found; configuration uses environment variables.
Similar Servers
Context-Engine
Self-improving code search and context engine for IDEs and AI agents, providing hybrid semantic/lexical search, symbol graph navigation, and persistent memory.
claude-conversation-memory-mcp
Provides long-term memory for AI coding agents by indexing conversation history, tracking decisions and mistakes, and enabling semantic search across projects.
mcp-raganything
Provides a FastAPI REST API and MCP server for Retrieval Augmented Generation (RAG) capabilities, integrating with the RAG-Anything and LightRAG libraries for multi-modal document processing and knowledge graph operations.
cldcde
A persistent context manager that scrapes, stores, searches, and analyzes AI conversations from various platforms (ChatGPT, Grok, Gemini, Claude) to support project development and insights.