Injection Detector
by viridis-security.com in Security & trust
Formally-verified injection/exfiltration detector for AI agents (MCP-02).
https://mcp.viridis-security.com/mcp- Tools
- 2
- open to any client
- Uptime
- 100%
- last 30 days
- Response time
- 396 ms
- 525 ms slowest 5%
- Last check
- Passed
- 9 h ago, next any minute now
Reliability
Status and outage history · Atom feed · Watch with other listings
How to connect
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"injection-detector": {
"type": "http",
"url": "https://mcp.viridis-security.com/mcp"
}
}
}2 tools
- 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…
- 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…
Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 9 h ago | Passed | 200 | 456 ms |
| 24 h ago | Passed | 200 | 370 ms |
| 38 h ago | Passed | 200 | 423 ms |
| 2 days ago | Passed | 200 | 359 ms |
| 3 days ago | Passed | 200 | 337 ms |
Show 10 older checks
| 3 days ago | Passed | 200 | 415 ms |
| 4 days ago | Passed | 200 | 507 ms |
| 4 days ago | Passed | 200 | 346 ms |
| 5 days ago | Passed | 200 | 380 ms |
| 5 days ago | Passed | 200 | 386 ms |
| 6 days ago | Passed | 200 | 374 ms |
| 6 days ago | Passed | 200 | 387 ms |
| 7 days ago | Passed | 200 | 437 ms |
| 7 days ago | Passed | 200 | 409 ms |
| 8 days ago | Passed | 200 | 360 ms |