Skip to main content
Glama
Sign In
vulnerability-exposure-mcp

vulnerability-exposure-mcp

by MRFrazer25
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Am I affected?

am_i_affected
Read-onlyIdempotent

Checks whether given software versions, lockfiles, or CycloneDX SBOMs are affected by a specific CVE or lists confirmed CVEs, returning AFFECTED, NOT_AFFECTED, or CANT_CONFIRM.

Instructions

Is my software affected? Give the products and versions you run (typed, or pasted from a banner or Server header), a lockfile (pinned requirements.txt, package-lock.json) or a CycloneDX SBOM. With cve_id, answers whether that one CVE (e.g. one in the news) affects each of them; without it, lists the confirmed CVEs for each. Every product gets AFFECTED, NOT_AFFECTED or CANT_CONFIRM with the NVD range, package advisory or distro fix that decided it. Lockfile and SBOM packages are checked in one OSV.dev batch call. 'nginx 1.24.0 -> 1.26.2' also shows what the upgrade fixes.

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": "am_i_affected"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoOptional. The path to one requirements*.txt, package-lock.json or CycloneDX JSON file the user named, for files too large to pass as text. Read-only; folders are never searched.
sbomNoOptional. The text of a CycloneDX JSON SBOM, e.g. from 'syft dir:. -o cyclonedx-json'.
cve_idNoOptional. One CVE ID, e.g. 'CVE-2024-6387', to ask whether that CVE affects this software. Leave it out to check for every known CVE.
lockfileNoOptional. The text of a pinned requirements.txt or a package-lock.json.
softwareNoThe software you run, one entry per product: 'nginx 1.24.0', a banner such as 'OpenSSH_8.9p1 Ubuntu-3ubuntu0.6', or a header such as 'Server: Apache/2.4.49 (Unix) OpenSSL/1.1.1k'. Add ' -> 1.26.2' to an entry to see what upgrading fixes. Up to 20 products.
investigation_idNoThe investigation_id from investigate_target. Pass it so the result counts toward that investigation's evidence, budget and key facts; without it the lookup runs on its own.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover read-only/no-destructive/idempotent, so the description focuses on what the annotations cannot say: the three verdict classes (AFFECTED, NOT_AFFECTED, CANT_CONFIRM), that each verdict carries its deciding NVD range/advisory/distro fix, and that lockfile/SBOM packages are resolved in one OSV.dev batch call. It omits what CANT_CONFIRM actually means in practice and any coverage caveats, keeping it below a 5.

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 question and the input forms, then layers mode behavior and verdict semantics; nearly every sentence carries distinct information. It is on the dense side with several parenthetical asides, which costs a point.

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?

There is no output schema, so the description must describe returns — it does, at the level of verdict values plus the deciding range/advisory and the batch-check behavior. It does not sketch the output shape (e.g. per-product grouping, CVE ID lists in the no-cve_id path), which is the remaining gap for a tool with no output schema.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns above that by explaining the interaction between parameters (cve_id toggles between single-CVE and full-scan mode) and by advertising the 'nginx 1.24.0 -> 1.26.2' upgrade-simulation syntax at the top level where an agent will read it.

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+resource ('is my software affected' / CVE exposure for my products) and enumerates accepted inputs (typed banners, lockfile, CycloneDX SBOM). It is clearly distinguishable from sibling lookups like nvd_lookup or version_specific_vulnerability_check because it takes the user's own inventory rather than a query key.

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?

Explicitly explains the two modes: with cve_id it answers about one CVE, without it lists all confirmed CVEs, which is exactly the when-to-use signal an agent needs. It does not name the sibling (version_specific_vulnerability_check) or state when that alternative is preferable, so it stops short of a 5.

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