Security review

Is TinyFish MCP safe to give an agent?

destructive capableverifiedhealthy

A factual risk summary built from TinyFish’s real tool surface, execution model, and verification history — not a vibe.


01What it can do

Has tools that can delete or irreversibly change data.

15 tools observeddestructive presentwrite present

02Execution model

Runs on the vendor's infrastructure; you connect over the network. No untrusted code runs on your machine, but you grant the hosted service access.

Installs via npx (`npx @tiny-fish/mcp`) — it pulls and executes third-party code; pin versions and review the source.


03Permissions & auth
api_keyoauth

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


04Verification
handshakenot confirmed
runsmetadata:passed · handshake:skipped · tools_list:passed
last_checked2026-09-22 18:29Z
sourcesUser submissions [p7]

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