Is Vaaya MCP safe to give an agent?

destructive capableverifieddestructive capablehealthy

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

01What it can do

Has tools that can delete or irreversibly change data.

44 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.

Connects to a remote URL — no local package execution.

03Permissions & auth

Knowledge & memory · writeVector & semantic search · writeManage docs & notes · writeRead email · destructiveUpdate a CRM · writeRead & write files · writeSearch the web · writeManage GitHub · writeProcess payments · writeRead calendar · writeScrape a website · writeSend chat messages · writeSchedule a meeting · writeExecute code · writeWorkflow automation · writeSocial selling & outreach · destructive

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_checked2026-10-05 06:42Z

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