CVE MCP Server

check_package

Check a specific package version for known CVE/GHSA vulnerabilities and malicious-package reports across npm, PyPI, Maven, Go, and more via OSV.dev, with real-world exploitation and EPSS risk signals.

Instructions

Check whether a specific package version has known vulnerabilities (CVE/GHSA, and malicious-package reports) via OSV.dev. Ecosystems: npm, Packagist, PyPI, Maven, Go, crates.io, NuGet, RubyGems, etc. Each result includes exploited (listed in CISA's Known Exploited Vulnerabilities = attacked in the wild now) and epss (FIRST probability of exploitation in the next 30 days, 0-1).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ecosystem": "<ecosystem>",
      "name": "<name>",
      "version": "<version>"
    },
    "name": "check_package"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	e.g. laravel/framework, axios
`version`	Yes	Installed version, e.g. 10.48.2
`ecosystem`	Yes	e.g. npm, Packagist, PyPI

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.2.0Nov 3, 2026

TDQS

A3.7/5.0

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 add real context: the external data source (OSV.dev), the inclusion of malicious-package reports, and the precise meaning of the returned `exploited` and `epss` fields. It does not state that the call is read-only, whether network latency or rate limits apply, or what an empty/no-vulnerability result looks like.

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?

Three sentences, front-loaded with the core action, then ecosystem coverage, then return-field semantics. No sentence is redundant and nothing is buried at the end.

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?

With no output schema, the description correctly compensates by defining the two most decision-relevant result fields, and it covers all three required parameters. It stops short of describing the result shape as a whole (advisory IDs, severity, affected ranges) or the no-findings case.

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, but the description earns a bump by enumerating supported ecosystems (Maven, Go, crates.io, NuGet, RubyGems) far beyond the three examples in the schema's ecosystem field — meaningful since no enum is enforced. Version and name semantics stay at schema level.

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

Purpose4/5

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

States a specific verb and resource ('Check whether a specific package version has known vulnerabilities') plus the backing service (OSV.dev), and the phrase 'a specific package version' implicitly contrasts with the bulk-oriented sibling scan_lockfile. It never names a sibling explicitly, so an agent must infer the boundary itself.

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

Usage Guidelines3/5

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

The single-package scope implies when to use this over scan_lockfile (one known dependency vs. an entire lockfile), and the mention of CVE/GHSA hints at overlap with get_cve. No explicit when-to-use or when-not-to-use statement or alternative is named, so guidance remains inferred.

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

Deploy Server