# Aguara MCP (oci · ghcr.io/garagon/mcp-aguara:0.8.0)

Scan skills, MCP configs, and agent content for injection and supply-chain risks. Offline, no LLM.

- Trust score: 40/100 (low)
- Change this week: −1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- oci · `ghcr.io/garagon/mcp-aguara:0.8.0`: 40/100 (this document), [markdown](https://verifymcp.io/servers/garagon-mcp-aguara/ghcr-io-garagon-mcp-aguara-0-8-0.md), [page](https://verifymcp.io/servers/garagon-mcp-aguara/ghcr-io-garagon-mcp-aguara-0-8-0)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/garagon/mcp-aguara:0.8.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-08-04.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - CVE data not yet available for this package.
  - Install-script risk not yet assessed.
  - Dependency-health data not yet available.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 33 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 992 tokens (~198/item across 5 items; 5 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add garagon-mcp-aguara -- docker run --rm -i ghcr.io/garagon/mcp-aguara:0.8.0
```

### Codex

```bash
codex mcp add garagon-mcp-aguara -- docker run --rm -i ghcr.io/garagon/mcp-aguara:0.8.0
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "garagon-mcp-aguara": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/garagon/mcp-aguara:0.8.0"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  garagon-mcp-aguara:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/garagon/mcp-aguara:0.8.0"]
```

### Other

```json
{
  "mcpServers": {
    "garagon-mcp-aguara": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/garagon/mcp-aguara:0.8.0"
      ]
    }
  }
}
```

## 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.

### 2026-08-04 (score 40, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-07-31 (score 36, −5)

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

### 2026-07-27 (score 41, +30)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: good
- [functional] First check of Schema quality: fail

### 2026-07-26 (score 11)

First indexed and scored.

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

## MCP tools (5)

### `check_mcp_config` (~196 tokens)

Check an MCP server configuration (JSON) for security issues before adding it to a client. Detects dangerous command shapes in `command`/`args`, credential exposure in `env`, unsafe argument injection, and tool-poisoning patterns. Use on any MCP server config block (`mcpServers` entries from Claude Desktop, Cursor, VS Code, etc.) before installing or enabling it. Sensitive matches are redacted in the response.

Input parameters:

- `config` (string, required): The MCP configuration as a JSON string
- `disabled_rules` (array): List of rule IDs to disable (e.g., ["PROMPT_INJECTION_001"])
- `min_severity` (string): Minimum severity to report: INFO, LOW, MEDIUM, HIGH, or CRITICAL
- `scan_profile` (string): Scan profile: strict (default, all rules), content-aware (reduced FP for known tools), or minimal (flag-only mode)

### `discover_mcp` (~86 tokens)

Discover MCP server configurations on the local machine by reading known MCP client config files (Claude Desktop, Cursor, VS Code, Windsurf, and others). Returns the server definitions including commands, arguments, and environment variables. Read-only: this tool never executes the discovered commands and never connects to any server; pair with `check_mcp_config` to evaluate each definition before acting on it.

### `explain_rule` (~121 tokens)

Get detailed information about a specific security rule by ID. Resolves both YAML rules (returns patterns plus true/false-positive examples) and analyzer-emitted rules from ci-trust, pkgmeta, jsrisk, pyrisk, rsbuild, npm-policy, pnpm-policy, agent-policy, NLP, toxic-flow, and rug-pull (returns severity, category, analyzer name, description, and remediation; analyzer rules have no inline patterns or examples).

Input parameters:

- `rule_id` (string, required): The rule ID to explain (e.g., PROMPT_INJECTION_001)

### `list_rules` (~151 tokens)

List the security rules cataloged by Aguara. Returns 250 detections (193 YAML pattern rules + 57 analyzer-emitted rules from ci-trust, pkgmeta, jsrisk, pyrisk, rsbuild, npm-policy, pnpm-policy, agent-policy, NLP, toxic-flow, and rug-pull analyzers) spanning multiple threat categories. Optionally filter by category (e.g. `prompt-injection`, `exfiltration`, `credential-leak`, `supply-chain`, `mcp-attack`, `toxic-flow`, `agent-trust`).

Input parameters:

- `category` (string): Filter rules by category (e.g., prompt-injection, exfiltration, credential-leak)

### `scan_content` (~398 tokens)

Scan text for security threats before acting on it. Works on agent skills, READMEs, tool definitions, MCP server descriptions, prompts, package manifest content (package.json), GitHub Actions workflow YAML when filename contains `.github/workflows/`, Claude Code settings when filename is `.claude/settings.json` or `.claude/settings.local.json`, agent instruction files (`.cursorrules`, `.windsurfrules`, `.clinerules`, `AGENTS.md`, `copilot-instructions.md`), npm install-trust policy when filename is `.npmrc` or `package.json`, and pnpm policy when filename is `pnpm-workspace.yaml`. Detects prompt injection (pattern + NLP), credential leaks, data exfiltration, command execution, supply-chain patterns, MCP attacks, package metadata risks, JavaScript / Python / Rust install-time payload shapes, GitHub Actions trust chains, risky agent host configuration, weakened npm / pnpm supply-chain settings, and Unicode / encoding evasion. Findings are categorized by severity with remediation hints. Sensitive matches are redacted before output. Supports context-aware false-positive reduction via tool_name.

Input parameters:

- `content` (string, required): The text content to scan (e.g., skill description, README, tool definition)
- `disabled_rules` (array): List of rule IDs to disable (e.g., ["PROMPT_INJECTION_001"])
- `filename` (string): Filename hint for the content (affects rule matching). Default: skill.md
- `min_severity` (string): Minimum severity to report: INFO, LOW, MEDIUM, HIGH, or CRITICAL
- `scan_profile` (string): Scan profile: strict (default, all rules), content-aware (reduced FP for known tools), or minimal (flag-only mode)
- `tool_name` (string): Tool that generated the content (e.g., Bash, Edit, WebFetch). Enables context-aware false-positive reduction

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/garagon-mcp-aguara/ghcr-io-garagon-mcp-aguara-0-8-0#diagnostics

## Score history

- 2026-08-04: 40
- 2026-08-03: 36
- 2026-08-02: 36
- 2026-08-01: 36
- 2026-07-31: 36
- 2026-07-30: 41
- 2026-07-29: 41
- 2026-07-28: 41
- 2026-07-27: 41
- 2026-07-26: 11

## Links

- Repository: https://github.com/garagon/mcp-aguara
- Changelog RSS feed: https://verifymcp.io/servers/garagon-mcp-aguara/ghcr-io-garagon-mcp-aguara-0-8-0/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/garagon-mcp-aguara/ghcr-io-garagon-mcp-aguara-0-8-0/changelog.json
- HTML version of this page: https://verifymcp.io/servers/garagon-mcp-aguara/ghcr-io-garagon-mcp-aguara-0-8-0