# io.github.viridis-security/injection-detector (remote · mcp.viridis-security.com)

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

- Trust score: 60/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.viridis-security.com`: 60/100 (this document), [markdown](https://verifymcp.io/servers/viridis-security-injection-detector/mcp.md), [page](https://verifymcp.io/servers/viridis-security-injection-detector/mcp)

## Channel facts

- Endpoint: `https://mcp.viridis-security.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 2 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 39/100
  - AI-judged instruction clarity (poor).
  - Context-footprint check failed: tool/resource definitions use about 344 tokens (~172/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

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

### Codex

```toml
[mcp_servers.viridis-security-injection-detector]
url = "https://mcp.viridis-security.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "viridis-security-injection-detector": {
      "type": "remote",
      "url": "https://mcp.viridis-security.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add viridis-security-injection-detector --url https://mcp.viridis-security.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  viridis-security-injection-detector:
    url: "https://mcp.viridis-security.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "viridis-security-injection-detector": {
      "type": "http",
      "url": "https://mcp.viridis-security.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 59, −3)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional improvement] Schema quality: 212 → 172
- [functional] Schema quality: fair → poor
- [functional] Server version: 0.1.0 → 0.2.0
- [functional] New tool “detect_trace_tool_policy”

### 2026-07-31 (score 62, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 61, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 59, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 58)

First indexed and scored.

## MCP tools (2)

### `detect_injection` (~171 tokens)

Detect adversarial 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.

Input parameters:

- `agentId` (string): Optional: for MCP-01 envelope cross-check.
- `certainty` (string): Operating point. Default standard.
- `context` (string): Optional: the agent's role/system prompt; helps calibrate.
- `input` (string, required): The untrusted text/data to screen.

Output parameters:

- `backedBy` (array)
- `bitsAtRisk` (number)
- `explainabilityToken` (string)
- `matchedPatterns` (array)
- `operatingPoint` (object)
- `probability` (number)
- `recommendedAction` (string)
- `signals` (object)
- `verdict` (string)

### `detect_trace_tool_policy` (~136 tokens)

Detect trace tool-policy violations

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.

Input parameters:

- `targetName` (string): Optional display name for the assessed target.
- `trace` (object): Single agent trace with user_prompt, allowed_tools, and events[].
- `traces` (array): Optional batch of agent traces.

Output parameters:

- `canonId` (string)
- `claimBoundary` (string)
- `customerSystemProved` (boolean)
- `explainabilityToken` (string)
- `mode` (string)
- `probability` (number)
- `recommendedAction` (string)
- `reviewPriority` (array)
- `summary` (object)
- `theoremRefs` (array)
- `traces` (array)
- `verdict` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/viridis-security-injection-detector/mcp#diagnostics

## Score history

- 2026-08-03: 60
- 2026-08-02: 59
- 2026-08-01: 62
- 2026-07-31: 62
- 2026-07-30: 61
- 2026-07-29: 60
- 2026-07-28: 60
- 2026-07-27: 59
- 2026-07-26: 58

## Links

- Remote endpoint: https://mcp.viridis-security.com/mcp
- Repository: https://github.com/viridis-security/mcp-services-sdk
- Changelog RSS feed: https://verifymcp.io/servers/viridis-security-injection-detector/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/viridis-security-injection-detector/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/viridis-security-injection-detector/mcp