Security review

Is Mailtrap MCP safe to give an agent?

destructive capableneeds cautiondestructive capablehealthy

A factual risk summary built from Mailtrap’s real tool surface, execution model, and verification history — not a vibe. Trust score 40/100.

01What it can do

Has tools that can delete or irreversibly change data.

105 tools observeddestructive presentwrite present

02Execution model

Runs locally over stdio — the server process executes on your machine with your user's privileges. Vet the source and package before granting access.

Installs via npx (`npx -y mcp-mailtrap`) — it pulls and executes third-party code; pin versions and review the source.

03Permissions & auth

Update a CRM · destructiveSend email · writeWorkflow automation · destructiveRead email · destructive

The write/destructive access this server can exercise, inferred from its verified tools.

04Verification

handshakenot confirmed

runshandshake:failed · metadata:passed · handshake:failed · metadata:passed · handshake:failed · metadata:passed · handshake:failed · metadata:passed · handshake:failed · metadata:passed

last_checked2026-08-16 21:33Z

sourcesAwesome MCP Servers (wong2) [p6]

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