Security review

Is ai.proxyllm/proxyllm-mcp MCP safe to give an agent?

write capableneeds cautionwrite capablehealthy

A factual risk summary built from ai.proxyllm/proxyllm-mcp’s real tool surface, execution model, and verification history — not a vibe. Trust score 52/100.

01What it can do

Has tools that can create or modify data.

9 tools observedwrite present

02Execution model

Runs locally over stdio — the server process executes on your machine with your user's privileges. Vet the source and package before granting access.

Installs via npx (`npx -y proxyllm-mcp`) — it pulls and executes third-party code; pin versions and review the source.

03Permissions & auth

This server has write tools. No auth scopes are recorded for how that access is granted.

04Verification

handshakenot confirmed

runsmetadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed · metadata:passed

last_checked2026-10-13 06:12Z

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