mcp-hello-world / security
Security review
Is mcp-hello-world MCP safe to give an agent?
write capableunknownunmaintainedhealthy
A factual risk summary built from mcp-hello-world’s real tool surface, execution model, and verification history — not a vibe. Trust score 47/100.
01What it can do
Has tools that can create or modify data.
3 tools observedwrite present
02Execution model
Transport not yet confirmed, so the execution model is unknown. Treat as untrusted until verified.
Installs via npx (`npx -y mcp-hello-world`) — it pulls and executes third-party code; pin versions and review the source.
03Permissions & auth
This server has write tools. No auth scopes are recorded for how that access is granted.
04Verification
handshakepassed — tool surface is real
runsmetadata:passed · metadata:passed · metadata:passed · tools_list:passed · handshake:passed · metadata:passed · tools_list:passed · handshake:passed · metadata:passed · tools_list:passed
last_checked2026-11-07 02:51Z
sourcesnpm registry [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