mcp-use / security
Security review
Is mcp-use MCP safe to give an agent?
unknownunknownunknownhealthy
A factual risk summary built from mcp-use’s real tool surface, execution model, and verification history — not a vibe. Trust score 58/100.
01What it can do
No tool handshake yet — capability surface unverified.
0 tools observed
02Execution model
Transport not yet confirmed, so the execution model is unknown. Treat as untrusted until verified.
Installs via npx (`npx -y mcp-use`) — it pulls and executes third-party code; pin versions and review the source.
03Permissions & auth
No write or destructive tools observed. Absence of a scope isn’t a guarantee — treat unconfirmed access as unknown, not “none.”
04Verification
handshakenot confirmed
runsmetadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed
last_checked2026-11-15 12:23Z
sourcesnpm 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