Injection Detector

io.github.viridis-security/injection-detector

Formally-verified injection/exfiltration detector for AI agents (MCP-02).

healthy

status

tools exposed

757ms

connect latency

9bdf8faf75c0

schema fingerprint

Tools (1)

detect_injection

Screen untrusted input for prompt/tool injection, exfiltration, and obfuscation before an agent consumes it. Returns a verdict (clean|suspicious|attack), probability, bits-at-risk (upper bound on adversarial capture per the Adversarial Landauer bound), matched canon patterns, and a recommended actio

Endpoint

https://mcp.viridis-security.com/mcp
Category: AI & LLM · Last checked: 2026-07-30T14:00:11Z

Monitor your own MCP server

Get alerted the moment yours goes down, a tool schema drifts, or an upstream silently breaks.

Get early access

How we measure →

What this means. This server responded to the MCP handshake and listed its tools without authentication. The schema fingerprint lets us flag if tool signatures silently change (schema drift) between checks.