What it does
Arbiter runs security checks on applications built with AI. It looks for leaked keys, open routes and database rules, and gives a fix for each issue it reports.
It fits projects where these three kinds of exposure are the concern. The source describes no other checks or supported stacks.
The source gives no details on installation, configuration or how results are returned.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Arbiter
Security checks for apps built with AI: leaked keys, open routes, database rules, each with a fix.
v0.1.0As shown on registry.modelcontextprotocol.io when we last read it