modelcontextprotocol-server-memory / security
Security review
Is servers MCP safe to give an agent?
destructive capableunknownofficialhealthy
A factual risk summary built from servers’s real tool surface, execution model, and verification history — not a vibe. Trust score 93/100.
01What it can do
Has tools that can delete or irreversibly change data.
9 tools observeddestructive presentwrite present
02Execution model
Transport not yet confirmed, so the execution model is unknown. Treat as untrusted until verified.
Installs via npx (`npx -y @modelcontextprotocol/server-memory`) — it pulls and executes third-party code; pin versions and review the source.
03Permissions & auth
Knowledge & memory · destructive
The write/destructive access this server can exercise, inferred from its verified tools.
04Verification
handshakepassed — tool surface is real
runsmetadata:passed · tools_list:passed · handshake:passed · metadata:passed · tools_list:passed · handshake:passed · metadata:passed · tools_list:passed · handshake:passed · metadata:passed
last_checked2026-08-16 20:16Z
sourcesAwesome MCP Servers (wong2) [p6] · npm registry [p4] · GitHub repo search [p4]
Reduce the risk
Worried about handing an agent raw access? See governed agents in action — Apex gives your AI paced, capped, fully-logged hands with approval queues before anything runs.
Explore Apex →See also: full server page · setup · alternatives