Skip to main content
Glama
jowhee327

aws-security-mcp

by jowhee327
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

scan_ecr_image_cve

Deep-scan ECR image layers to find critical and high CVEs missed by standard scans, with classification against official results.

Instructions

Deep-scan ECR image layers for critical/high CVEs missed by ECR Basic/Inspector Enhanced scanning (unmanaged binaries, distro secdb gaps). Reports gap/confirmed/reverse-gap classification against official scan results. Read-only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
regionNoAWS region to scan (default: server region)
providerNoCloud provider to scan (default: aws). With huaweicloud, `region` is a Huawei Cloud region ID (e.g. cn-north-4); omit it or pass "all" to scan every region project of the account. Huawei Cloud Phase 1 is single-account (org_mode falls back to the current account with a warning).
min_severityNoMinimum CVE severity to report (default: high)
suppressionsNoFalse-positive suppression list; suppressed findings go to a suppressed[] section
max_image_bytesNoSkip images whose compressed layers total more than this many bytes (default: 2 GB)
max_layer_bytesNoSkip images containing a layer larger than this many compressed bytes (default: 512 MB)
max_total_bytesNoCumulative cap on compressed layer bytes downloaded across the whole scan (default: 20 GB)
max_repositoriesNoMaximum number of repositories to scan; the rest are recorded in warnings (default: 50)
include_confirmedNoInclude confirmed finding detail rows in the report (default: false)
online_cve_lookupNoEnable NVD API 2.0 online lookup, cached 24h (default: false)
repository_filterNoGlob filter on ECR repository names (e.g. prod-*)
max_images_per_repoNoLatest-pushed N images per repo, plus any tag named 'latest' (default: 3)
platform_preferenceNoPlatform preference order for multi-arch manifest lists, e.g. ['linux/amd64', 'linux/arm64'] (default)
max_binary_scan_bytesNoCap on decompressed bytes stream-scanned per candidate binary (default: 64 MB)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.9.0
    • addedInput schema / properties / provider
      Added value: +{
+  "description": "Cloud provider to scan (default: aws). With huaweicloud, `region` is a Huawei Cloud region ID (e.g. cn-north-4); omit it or pass \"all\" to scan every region project of the account. Huawei Cloud Phase 1 is single-account (org_mode falls back to the current account with a warning).",
+  "enum": [
+    "aws",
+    "huaweicloud"
+  ],
+  "type": "string"
+}
  2. Addedv0.8.0

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses that the tool is read-only, that it performs deep scanning of image layers, that it reports classifications against official scan results, and that it can skip images based on size limits. It doesn't disclose rate limits, NVD API behavior beyond the parameter description, or what happens to partial results, but the core behavioral traits are clearly stated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences with zero waste. The core purpose and differentiator are front-loaded, the classification output is stated, and the read-only nature is appended. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 14-parameter scan tool with no output schema, the description is reasonably complete: it states the purpose, the classification output, and the read-only nature. It doesn't describe the report structure or how results are returned, but the parameter descriptions cover the behavioral knobs. The lack of an output schema is a gap, but the description does enough to let an agent invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 14 parameters thoroughly. The description adds context about the overall scan behavior (deep-scan, classification) but doesn't add much per-parameter meaning beyond what the schema provides. Baseline 3 is appropriate because the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Deep-scan'), a specific resource ('ECR image layers'), and a specific scope ('critical/high CVEs missed by ECR Basic/Inspector Enhanced scanning'). It also names the classification output ('gap/confirmed/reverse-gap') and explicitly says 'Read-only', which distinguishes it from other scan tools. This is a clear, differentiated purpose statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use this tool: when you need deeper CVE detection beyond ECR Basic/Inspector Enhanced, specifically for unmanaged binaries and distro secdb gaps. It doesn't explicitly name sibling alternatives or state when not to use it, but the contrast with 'ECR Basic/Inspector Enhanced scanning' provides clear context. The 'Read-only' note also helps an agent choose it over mutation tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools