aws-security-mcp

prioritize_vulnerabilities

Rank CVE vulnerabilities by exploitability using exploit intel, EPSS, CISA KEV, and AWS exposure context to show which findings to fix first. Read-only prioritization; no active probing.

Instructions

List CVE vulnerabilities ordered by exploitability priority (P0 first) using threat intel (public exploit, EPSS, CISA KEV) and configured exposure (public IP, security groups, NACLs, running state). Pulls Inspector2 findings directly, falling back to the Security Hub Inspector subset. Prioritization only — not penetration testing; read-only, no active probing. AWS only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "prioritize_vulnerabilities"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Maximum items to return (default: 20, max: 200)
`region`	No	AWS region to scan (default: server region)
`provider`	No	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). With alicloud (EXPERIMENTAL — not yet validated against a live account), region is an Alibaba Cloud region ID (e.g. cn-hangzhou); omit or "all" to scan every region; single-account only in this phase. With azure (EXPERIMENTAL — not yet validated against a live account), the China cloud (21Vianet) is the default; set AZURE_CLOUD=global for public cloud. region is an Azure subscription ID; omit or "all" to scan every visible subscription.
`priorities`	No	Exploitability priorities to return (default: ["P0","P1"])
`resource_type`	No	Only return findings on this resource type (default: all)
`include_reachability`	No	Resolve network reachability (EC2/ECS/Lambda, read-only API calls). false is faster and leaves reachability unknown (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.10.0Nov 8, 2026

TDQS

A3.9/5.0

Behavior3/5

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

With no annotations, the description carries the full burden and does disclose key traits: read-only, no active probing, source precedence (Inspector2 first, Security Hub fallback), and that include_reachability triggers read-only API calls. However, it omits permission requirements, rate/volume behavior, and what happens when neither source has data, and its 'AWS only' claim sits awkwardly against a provider enum that lists huaweicloud, alicloud, and azure.

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

Conciseness4/5

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

Front-loaded with the core action and ordering, then supporting detail in short clauses. It is dense but every clause carries information; the trailing fragments ('Prioritization only — not penetration testing; read-only, no active probing. AWS only.') are efficient rather than padded.

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 read-only listing tool with no output schema, the description conveys the return shape (CVE list ordered P0 first) and the scoring inputs (public exploit, EPSS, CISA KEV, exposure factors), which is enough to call it correctly. Minor gaps remain around empty-result behavior and the provider/AWS-only discrepancy.

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 limit, region, provider, priorities, resource_type, and include_reachability in detail. The description adds only the general notion of 'configured exposure' and does not clarify parameter interactions or defaults beyond what the schema states, so baseline 3 applies.

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?

States a specific verb and resource ('List CVE vulnerabilities') plus the ordering rule ('ordered by exploitability priority, P0 first') and the data sources used. It also distinguishes itself from raw-finding siblings by noting it pulls Inspector2 findings and falls back to the Security Hub Inspector subset, so an agent can tell it apart from scan_inspector_findings or scan_security_hub_findings.

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?

Gives a clear when-not ('Prioritization only — not penetration testing; read-only, no active probing') and a scope constraint ('AWS only'), which helps an agent avoid picking it for active scanning. It does not explicitly name a sibling alternative for raw findings, so it stops short of full routing guidance.

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

Deploy Server