Server data from the Official MCP Registry
Long-term memory for AI coding tools via vector search (Qdrant).
Long-term memory for AI coding tools via vector search (Qdrant).
Set these up before or after installing:
Environment variable: NAN_FORGET_QDRANT_URL
Environment variable: OPENAI_API_KEY
Environment variable: NAN_FORGET_EMBEDDING_PROVIDER
Environment variable: NAN_FORGET_USER_ID
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-nanmesh-nan-forget": {
"env": {
"OPENAI_API_KEY": "your-openai-api-key-here",
"NAN_FORGET_USER_ID": "your-nan-forget-user-id-here",
"NAN_FORGET_QDRANT_URL": "your-nan-forget-qdrant-url-here",
"NAN_FORGET_EMBEDDING_PROVIDER": "your-nan-forget-embedding-provider-here"
},
"args": [
"-y",
"nan-forget"
],
"command": "npx"
}
}
}This is a well-structured memory storage system for AI assistants with appropriate security practices. The code demonstrates good security hygiene with proper credential handling via environment variables, reasonable permissions that match its purpose as a developer tool, and clean architecture. Minor findings include some error handling improvements and dependency considerations, but these don't significantly impact the overall security posture. Supply chain analysis found 1 known vulnerability in dependencies (1 critical, 0 high severity). Package verification found 1 issue.
Scanned 6 files · 6 findings
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Be the first to review this server!