Back to Home
gregorydickson icon

memory-graph

Verified Safe

by gregorydickson

Overview

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.

Installation

Run Command
python -m memorygraph

Environment Variables

  • MEMORY_BACKEND
  • MEMORY_SQLITE_PATH
  • MEMORY_NEO4J_URI
  • MEMORY_NEO4J_USER
  • MEMORY_NEO4J_PASSWORD
  • MEMORY_MEMGRAPH_URI
  • MEMORY_MEMGRAPH_USER
  • MEMORY_MEMGRAPH_PASSWORD
  • MEMORY_FALKORDB_HOST
  • MEMORY_FALKORDB_PORT
  • MEMORY_FALKORDB_PASSWORD
  • MEMORY_FALKORDBLITE_PATH
  • MEMORYGRAPH_API_KEY
  • MEMORYGRAPH_TURSO_URL
  • MEMORYGRAPH_TURSO_TOKEN
  • MEMORY_MULTI_TENANT_MODE
  • MEMORY_DEFAULT_TENANT
  • MEMORY_REQUIRE_AUTH
  • MEMORY_JWT_SECRET
  • MEMORY_JWT_ALGORITHM
  • MEMORY_ENABLE_AUDIT_LOG
  • MEMORY_ALLOW_CYCLES
  • MEMORY_TOOL_PROFILE
  • LOG_LEVEL
  • CLAUDE_CODE_REMOTE

Security Notes

The server uses `subprocess.run` for Git commands, which is common in development tools and appears safely implemented (not using `shell=True`). It explicitly sanitizes sensitive information (API keys, tokens, passwords) from memory content and logs using `_sanitize_content`. Database credentials are primarily sourced from environment variables, avoiding hardcoding. Pydantic is used for input validation, mitigating common API injection risks. The `CloudBackend` uses `httpx` with circuit breaking for external network calls, enhancing resilience.

Similar Servers

Stats

Interest Score92
Security Score9
Cost ClassMedium
Avg Tokens1500
Stars91
Forks62
Last Update2025-12-05

Tags

memory-managementgraph-databaseAI-assistantknowledge-graphdeveloper-tools