Skip to main content
Glama

Dependency risk score

dependency_risk_score
Read-only

Score the security risk of software dependencies before using them. Checks each package against OSV.dev (Google's vulnerability database) and deps.dev for metadata. Returns per-package CVE counts, max severity, abandonment signals, and a hallucination check — HALLUCINATED means the package was not found and may be an AI-invented name or typosquat. Supports npm, pypi, go, maven, cargo, and nuget. Accepts up to 20 packages per call. Costs $0.10 USDC per call.

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": {
      "packages": "<packages>"
    },
    "name": "dependency_risk_score"
  }
}

Input Schema

NameRequiredDescriptionDefault
packagesYesJSON array of packages to scan. Each entry: {"name": "lodash", "ecosystem": "npm", "version": "4.17.19"} — version is optional. Ecosystems: npm, pypi, go, maven, cargo, nuget. Example: [{"name":"lodash","ecosystem":"npm"},{"name":"requests","ecosystem":"pypi"}]

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses upstream data sources, what the response contains (per-package CVE counts, max severity, abandonment signals), the meaning of the HALLUCINATED verdict, a hard cap of 20 packages, and a $0.10 USDC cost per call. Cost and quota disclosure is exactly the kind of operational context annotations cannot carry.

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?

Five tight sentences, front-loaded with purpose, then sources, then return shape, then limits, then cost. Every sentence carries a distinct fact; the only near-waste is re-listing ecosystems already enumerated in the schema.

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 carries the burden of explaining return values and does so (CVE counts, max severity, abandonment signals, hallucination verdict). Input format, ecosystem scope, package cap, cost, and failure semantics are all covered, leaving only the exact response field shapes unspecified.

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 packages format is already documented; the description nonetheless adds a constraint absent from the schema — the 20-package-per-call limit — and restates the supported ecosystems. The ecosystem repetition is minor redundancy but the cap is real added meaning, so slightly above baseline.

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 ('Score the security risk') plus the exact resource (software dependencies/packages), and names the data sources (OSV.dev, deps.dev). This is unmistakably distinct from crypto-domain siblings like token_risk_score or token_security, so an agent can route correctly without opening a schema.

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?

'Before using them' gives a clear trigger for when to call it, and the ecosystem list signals when it applies versus when it doesn't. However it never explicitly contrasts itself with the superficially similar risk/security siblings (token_risk_score, token_security, secrets_detection), leaving that disambiguation to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources