# AI Agent Security Audit (remote · llmrt-companion.manhliemcn4euwlu.workers.dev)

AI agent security audit: red-team probes plus missing-guardrail review with fixes.

- Trust score: 18/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `llmrt-companion.manhliemcn4euwlu.workers.dev`: 18/100 (this document), [markdown](https://verifymcp.io/servers/dev-workers-manhliemcn4euwlu-llmrt-companion-mcp-audit/mcp-audit.md), [page](https://verifymcp.io/servers/dev-workers-manhliemcn4euwlu-llmrt-companion-mcp-audit/mcp-audit)

## Channel facts

- Endpoint: `https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## 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 2026-11-05.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 530, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint returned HTTP 530.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the AI Agent Security Audit MCP server?

AI Agent Security Audit is a hosted endpoint at https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-workers-manhliemcn4euwlu-llmrt-companion-mcp 'https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-workers-manhliemcn4euwlu-llmrt-companion-mcp": {
      "url": "https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-workers-manhliemcn4euwlu-llmrt-companion-mcp": {
      "type": "http",
      "url": "https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-workers-manhliemcn4euwlu-llmrt-companion-mcp]
url = "https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-workers-manhliemcn4euwlu-llmrt-companion-mcp": {
      "type": "remote",
      "url": "https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-workers-manhliemcn4euwlu-llmrt-companion-mcp --url 'https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-workers-manhliemcn4euwlu-llmrt-companion-mcp:
    url: "https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-workers-manhliemcn4euwlu-llmrt-companion-mcp": {
      "Transport": "http",
      "Url": "https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-workers-manhliemcn4euwlu-llmrt-companion-mcp -t streamable-http -u 'https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit'
```

### Other

```json
{
  "mcpServers": {
    "dev-workers-manhliemcn4euwlu-llmrt-companion-mcp": {
      "type": "http",
      "url": "https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit"
    }
  }
}
```

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.

### 2026-11-05 (score 18, −36)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-11-04 (score 54)

First indexed and scored.

## MCP tools (5)

### `run_free_scan` (~113 tokens)

Free LLM agent security review in ~35s. Two parts: (1) 8 live adversarial probes (jailbreak / prompt injection / system-prompt extraction / tool abuse) against your agent spec, and (2) a deterministic static audit of which guardrails the spec text itself is missing. Returns a 0-100 risk score, per-finding evidence, and a paste-ready guardrail sentence for each gap.

Input parameters:

- `spec` (string, required): Your agent / system prompt (>=20 chars)

### `get_scan_result` (~35 tokens)

Poll a scan by job id (returned by run_free_scan) until status=done.

Input parameters:

- `job_id` (string, required)

### `get_pricing` (~53 tokens)

PRO pricing & payment info: 44 probes / 20 attack classes / 0-100 score / CI gate / per-class remediation, 0.15 XNO (ERC-20 or Lightning) or card.

### `get_purchase_flow` (~53 tokens)

Machine-readable autonomous purchase procedure: how an agent pays (0.15 XNO, or USDC on Base via x402) and receives the PRO download with no human in the loop (callback push + poll fallback).

### `validate` (~112 tokens)

Judge one delivery against the task's own acceptance rule and return {verdict: accepted|rejected, reason}. Called by the brick.blue hub when this seat is drawn as validator. Judges only machine-checkable criteria (json_schema / contains / fields); a task with no such rule is accepted, because rejecting needs evidence.

Input parameters:

- `attemptId` (string)
- `description` (string)
- `input`
- `result`
- `taskId` (string)
- `title` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-workers-manhliemcn4euwlu-llmrt-companion-mcp-audit/mcp-audit#diagnostics

## Score history

- 2026-11-05: 18
- 2026-11-04: 54

## Common questions

### What is the AI Agent Security Audit MCP server?

AI Agent Security Audit is an MCP server listed in the public MCP registry as dev.workers.manhliemcn4euwlu.llmrt-companion/mcp-audit. AI agent security audit: red-team probes plus missing-guardrail review with fixes. This page covers its hosted endpoint (https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit).

### Is the AI Agent Security Audit MCP server safe to use?

AI Agent Security Audit scores 18 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the AI Agent Security Audit MCP server expose?

AI Agent Security Audit exposes 5 tools: run_free_scan, get_scan_result, get_pricing, get_purchase_flow, validate. Their descriptions and schemas cost roughly 366 tokens of context every time the server is loaded.

### Does the AI Agent Security Audit MCP server require authentication?

Its publisher declares no required credentials for AI Agent Security Audit. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the AI Agent Security Audit MCP server still maintained?

AI Agent Security Audit is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://llmrt-companion.manhliemcn4euwlu.workers.dev/mcp-audit
- Website: https://llmrt-companion.manhliemcn4euwlu.workers.dev/agent
- Changelog RSS feed: https://verifymcp.io/servers/dev-workers-manhliemcn4euwlu-llmrt-companion-mcp-audit/mcp-audit.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-workers-manhliemcn4euwlu-llmrt-companion-mcp-audit/mcp-audit.json
- HTML version of this page: https://verifymcp.io/servers/dev-workers-manhliemcn4euwlu-llmrt-companion-mcp-audit/mcp-audit