Skip to main content
Glama

dependency_check

Read-only

Check dependency manifests. Price: free by default; with live: true, 2 credits up to 50 packages, +1 per further 50, max 5 (200 packages). Default: offline hygiene lint for unpinned, wildcard or unbounded versions, missing lockfiles, git/URL deps, non-https indexes, install scripts, dependency-confusion names, plus a static snapshot of famous compromised versions. live: true adds, per package, known vulnerabilities from OSV.dev (exact versions only), latest version, licence and deprecation from deps.dev, and one verdict: PASS, REVIEW or FAIL (FAIL at fail_on severity or above, a denied licence, or a compromised version). Use this for manifests you can paste; use supply_chain_scan for a whole repo ZIP or MCP configs. Send exactly one of manifests (1-20 files) or upload_id + filename. Reads package.json, package-lock.json, requirements.txt, pyproject.toml, Pipfile, go.mod, Gemfile, composer.json, pubspec.yaml. Nothing is installed or run. Bearer key required. Returns hygiene findings, a 0-100 score and grade A-F, and with live: true a live section with the verdict, per-package results and source attribution. Upstream outages are refunded (503 upstream_unavailable).

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": "dependency_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
liveNotrue adds live vulnerability, version, licence and deprecation lookups and a verdict, for 2-5 credits by package count. false (default) is the free offline hygiene check.
fail_onNoLive mode only: the lowest advisory severity that makes the verdict FAIL. Lower-severity or unrated advisories give REVIEW.high
filenameNoRequired with upload_id, e.g. package.json: the file name decides how the content is parsed.
manifestsNo1 to 20 manifest files inline, each up to 500,000 characters. Send exactly one of manifests or upload_id.
upload_idNoInstead of manifests: one manifest uploaded via the create_upload tool (your own uploads only). Send exactly one of manifests or upload_id.
include_devNoLive mode only: also look up dev dependencies.
licence_policyNoLive mode only: exactly one of allow or deny, a list of 1-100 SPDX licence ids. A package whose licence breaks the policy makes the verdict FAIL; an unknown licence gives REVIEW.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / fail_on
      Added value: +{
      +  "default": "high",
      +  "description": "Live mode only: the lowest advisory severity that makes the verdict FAIL. Lower-severity or unrated advisories give REVIEW.",
      +  "enum": [
      +    "critical",
      +    "high",
      +    "medium",
      +    "low"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / include_dev
      Added value: +{
      +  "default": false,
      +  "description": "Live mode only: also look up dev dependencies.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / licence_policy
      Added value: +{
      +  "description": "Live mode only: exactly one of allow or deny, a list of 1-100 SPDX licence ids. A package whose licence breaks the policy makes the verdict FAIL; an unknown licence gives REVIEW.",
      +  "properties": {
      +    "allow": {
      +      "description": "Only these licences pass.",
      +      "items": {
      +        "maxLength": 64,
      +        "type": "string"
      +      },
      +      "maxItems": 100,
      +      "minItems": 1,
      +      "type": "array"
      +    },
      +    "deny": {
      +      "description": "These licences fail.",
      +      "items": {
      +        "maxLength": 64,
      +        "type": "string"
      +      },
      +      "maxItems": 100,
      +      "minItems": 1,
      +      "type": "array"
      +    }
      +  },
      +  "type": "object"
      +}
    • addedInput schema / properties / live
      Added value: +{
      +  "default": false,
      +  "description": "true adds live vulnerability, version, licence and deprecation lookups and a verdict, for 2-5 credits by package count. false (default) is the free offline hygiene check.",
      +  "type": "boolean"
      +}
  2. Changed8 schema fields changed
    • changedInput schema / properties / filename / description
      Previous value: -"Required with upload_id so the manifest type can be detected."New value: +"Required with upload_id, e.g. package.json: the file name decides how the content is parsed."
    • changedInput schema / properties / manifests / description
      Previous value: -"Up to 20 manifest files inline."New value: +"1 to 20 manifest files inline, each up to 500,000 characters. Send exactly one of manifests or upload_id."
    • addedInput schema / properties / manifests / items / properties / content / description
      Added value: +"Full file text."
    • addedInput schema / properties / manifests / items / properties / content / maxLength
      Added value: +500000
    • addedInput schema / properties / manifests / items / properties / filename / description
      Added value: +"File name, e.g. package.json; drives type detection."
    • addedInput schema / properties / manifests / maxItems
      Added value: +20
    • addedInput schema / properties / manifests / minItems
      Added value: +1
    • changedInput schema / properties / upload_id / description
      Previous value: -"Alternative: a single manifest uploaded via the uploads tool."New value: +"Instead of manifests: one manifest uploaded via the create_upload tool (your own uploads only). Send exactly one of manifests or upload_id."
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the supplied readOnly/openWorld annotations by disclosing cost mechanics (free by default, 2 credits to 50 packages, +1 per further 50, max 5), auth requirements (Bearer key), the safety guarantee 'Nothing is installed or run', supported manifest formats, verdict derivation including fail_on and licence policy, and refund behavior on 503 upstream_unavailable.

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 purpose and price, then mode behavior, then routing, then I/O and error handling — a sensible order. The single dense paragraph packs several clauses per sentence (pricing tiers, verdict conditions, file list), which costs some scannability but no sentence is filler.

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

Completeness5/5

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

For a seven-parameter tool with nested objects and no output schema, the definition still describes the return shape (hygiene findings, 0-100 score, A-F grade, live section with verdict, per-package results and source attribution) plus the error contract. Nothing an agent needs to call it correctly or interpret the result is missing.

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 already 100%, so the baseline is 3; the description earns more by explaining the cost and capability consequence of live:true, how the verdict resolves against fail_on, and that include_dev and licence_policy are live-mode-only. It does not re-explain the enum values or the SPDX list format, which the schema already covers.

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 ('Check dependency manifests') and immediately scopes it against the sibling: 'use supply_chain_scan for a whole repo ZIP or MCP configs'. The two modes (offline hygiene lint vs. live vulnerability lookup) are each spelled out, so an agent can distinguish this tool from every other linter in the sibling list.

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

Usage Guidelines5/5

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

Explicit routing rules: pasteable manifests here, whole repos or MCP configs to supply_chain_scan, and 'Send exactly one of manifests (1-20 files) or upload_id + filename'. It also names create_upload as the source of upload_id, which removes the only ambiguous input path.

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.