Formally-verified injection/exfiltration detector for AI agents (MCP-02).
| Endpoint | https://mcp.viridis-security.com/mcp (streamable-http) |
|---|---|
| Registry version | 0.1.0 |
| Now | 2 tools · grade A (99) · pin ts_a2de151788df9c7d52f8d118ecb2e379 · protocol 2025-06-18 |
| First / last listed | 2026-11-09 01:52 UTC / 2026-11-09 01:52 UTC |
| Grade over time | 2026-11-09: A (99), 2 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: detect_injection detect_trace_tool_policy
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 action (allow|sanitize|reject|escalate). Backed by Aristotle-verified theorems T-IB-02/T-IB-06/T-IB-01. params: input*, context, certainty, agentId |
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-IB-36. params: trace, traces, targetName |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.