Security review

Is mcp-ssh-manager MCP safe to give an agent?

write capableneeds cautionwrite capablehealthy

A factual risk summary built from mcp-ssh-manager’s real tool surface, execution model, and verification history — not a vibe. Trust score 70/100.

01What it can do

Has tools that can create or modify data.

37 tools observedwrite 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-ssh-manager`) — it pulls and executes third-party code; pin versions and review the source.

03Permissions & auth

Manage cloud infra · writeQuery a database · destructiveRead & write files · write

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 23:02Z

sourcesGitHub 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