Security review

Is mrmarket.ai MCP safe to give an agent?

read onlyverifiedhealthyhealthy

A factual risk summary built from mrmarket.ai’s real tool surface, execution model, and verification history — not a vibe. Trust score 66/100.

01What it can do

Only read-style tools observed — no write/destructive tools.

9 tools observed

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

Process payments · writeMonitoring & logs · writeQuery a database · writeRead calendar · write

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

04Verification

handshakenot confirmed

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

last_checked2026-08-21 04:50Z

sourcesOfficial MCP Registry [p1]

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