mcp server
injection-detector
Formally-verified injection/exfiltration detector for AI agents (MCP-02).
Description as published by the maintainer. Source
- version 0.1.0
- active
active — Registry entry last updated 2026-05-30.
What this server can do
2 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
detect_injection(input, agentId, context, certainty)- 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. Required: input.
detect_trace_tool_policy(trace, traces, targetName)- 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.
Last successful function declaration observed on . Source: https://mcp.viridis-security.com/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://mcp.viridis-security.com/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Latest published version | 0.1.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-05-30 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-05-30 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| mcp tools declared | 2 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | mcp.viridis-security.com | |
| mcp endpoint status | ok | The server listed 2 functions when asked. | as of probe | mcp.viridis-security.com |
Where to get it
Also from viridis-security
-
Verdigraph — paid hosted MCP for compute routing
Paid hosted MCP for agent-to-agent compute routing. 25% of net revenue funds conservation.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json