MCP serverio.github.viridis-security/injection-detector

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

UNRATEDActivestreamable-httpmcp.viridis-security.com

Overview

Score?

UNRATED 0.742

of what a free look can see, on 30 looks

Looks

last 13 hr ago

Tools

URL

mcp.viridis-security.com/mcp

streamable-http

Says it is

viridis-injection-detector 0.2.0

protocol 2025-06-18

In the record since

32 days ago

0median 0.606 · this server 0.742 · highest on record 0.8561

The tools this server lists, read out of the definition it returned
Tool	Schema
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	input · output
detect_trace_tool_policy Analyze an agent trace for the Gray Swan Wave 16 class: untrusted retrieved/tool output causing a tool call outside the user-declared per-turn allowlist. Returns trace counts, unau	input · output

Verify it yourselfnpx teppi-check https://mcp.viridis-security.com/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M1FZ2NVJKS0KHY9Y9Q8AT9RX