ai-mcp-server / security
Security review
Is ai-mcp-server MCP safe to give an agent?
write capableunknownwrite capablehealthy
A factual risk summary built from ai-mcp-server’s real tool surface, execution model, and verification history — not a vibe. Trust score 37/100.
01What it can do
Has tools that can create or modify data.
6 tools observedwrite present
02Execution model
Transport not yet confirmed, so the execution model is unknown. Treat as untrusted until verified.
Installs via uvx (`uvx ai-mcp-server`) — it pulls and executes third-party code; pin versions and review the source.
03Permissions & auth
Generate images · writeVector & semantic search · write
The write/destructive access this server can exercise, inferred from its verified tools.
04Verification
handshakenot confirmed
runshandshake:failed · metadata:passed · handshake:failed · metadata:passed · handshake:failed · metadata:passed · handshake:failed · metadata:passed · handshake:failed · metadata:passed
last_checked2026-08-16 19:31Z
sourcesPyPI [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