raven / security
Security review
Is Raven MCP safe to give an agent?
write capableneeds cautionwrite capablehealthy
A factual risk summary built from Raven’s real tool surface, execution model, and verification history — not a vibe. Trust score 58/100.
01What it can do
Has tools that can create or modify data.
105 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 raven-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_checked2026-11-20 20:23Z
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