All servers · AI models & agents

io.github.viridis-security/injection-detector

io.github.viridis-security/injection-detector · v0.1.0

Instruction-like text in descriptionsNo registry update 90+ days

Measured by MCP Station

Last check	Reachable
Checked at	—
Check success 7 / 30 days	—
First-try success 30 days	—
Median response	—
Lookups 30 days	—
Authentication	No auth
MCP version	2025-06-18
Rank score	—
Declared risk	Not declared (tools carry no read/destructive hints)
Capabilities declared	tools
Tool definitions	2 tools · with description 100% · input schema is an object 100% · read/destructive hints 0%

Instruction-like text was found in detect_injection and the registry description. This is a pattern match, not a verdict. What we look for

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

streamable-http · https://mcp.viridis-security.com/mcp

claude mcp add --transport http injection-detector https://mcp.viridis-security.com/mcp

{
  "mcpServers": {
    "injection-detector": {
      "url": "https://mcp.viridis-security.com/mcp"
    }
  }
}

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
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, unauthorized tool-call evidence, canon mapping VC-AI-TOOL-0001, and claim-boundary guardrails. Backed by T-IB-25/T-IB-29/T-I

Repository · JSON · Text for agents · Registry updated 2026-05-30