Skip to content
ISSUE 001·LIVE·03:34 IL
← The Lab/016 · TOOL·Shipped 2026-06

AgentSentinel

A transparent MCP proxy that inspects every tool response for prompt injection attacks before the content reaches the model's context window.

AgentSentinel wraps any MCP server as a transparent proxy, scanning tool responses in real-time for prompt injection patterns before they reach the model. In detect mode it logs threats to a structured NDJSON feed; in block mode HIGH-severity injections are dropped before the model sees them. Ships with 8 detection patterns across LOW/MEDIUM/HIGH severity tiers and a live threat dashboard on GitHub Pages.

Build log

Get an email when I ship a new prototype or essay. No funnel — just the work.