Security review

Is FullEnrich MCP safe to give an agent?

write capableverifiedwrite capablehealthy

A factual risk summary built from FullEnrich’s real tool surface, execution model, and verification history — not a vibe. Trust score 36/100.

01What it can do

Has tools that can create or modify data.

9 tools observedwrite 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.

Connects to a remote URL — no local package execution.

03Permissions & auth

Update a CRM · writefullenrich:operate

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

04Verification

handshakenot confirmed

runshandshake:skipped · metadata:passed · handshake:skipped · metadata:passed

last_checked—

sourcesunknown

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