Injection Detector
Formally-verified injection/exfiltration detector for AI agents (MCP-02).
Connect it
Settings → Connectors → Add custom connector
URL: https://mcp.viridis-security.com/mcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://mcp.viridis-security.com/mcp{
"mcpServers": {
"injection-detector": {
"url": "https://mcp.viridis-security.com/mcp"
}
}
}claude mcp add --transport http injection-detector https://mcp.viridis-security.com/mcp{
"servers": {
"injection-detector": {
"type": "http",
"url": "https://mcp.viridis-security.com/mcp"
}
}
}2 tools, verified live
detect_injectionScreen 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 action (allow|sanitize|reject|escalate). Backed by Aristotle-verified theorems T-IB-02/T-IB-06/T-IB-01.
detect_trace_tool_policyAnalyze 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-IB-36.
Alternatives in Developer Tools
Compare →
Compiler ExplorerA
Compile code with thousands of compilers, inspect the assembly, and share godbolt.org links
MIMiroOfficialA
Official Miro MCP server - Supports context to code and creating diagrams, docs, and data tables.
Context7A
Up-to-date code docs for any prompt
AAAirbyte AgentsOfficialA
Let AI agents query data and act across all your business apps via MCP.
VirusTotalOfficialA
Official VirusTotal MCP server: threat reports, file and URL submissions, and analysis recovery.
NENetdataA
Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.