Skip to main content
Glama
artifacthub-mcp

artifacthub-mcp

by Ankur1911

package_details

Read-onlyIdempotent

Retrieve a consolidated Artifact Hub package profile with versions, vulnerabilities, dependencies, install references, maintainers, and trust signals to evaluate a package before use.

Instructions

One-call profile of a package: description, versions (latest plus recent releases with dates and security-update flags), install reference, chart dependencies, container images, vulnerability summary, source links, maintainers, signing, publisher trust flags, stars and production-usage count. Readme text is left out on purpose.

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": {
      "kind": "<kind>",
      "repo": "<repo>",
      "name": "<name>"
    },
    "name": "package_details"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesPackage kind as used by Artifact Hub, e.g. 'helm' (charts), 'olm' (operators), 'krew', 'container', 'kyverno', 'opa', 'falco', 'backstage', 'keda-scaler', 'tekton-task', 'argo-template'.
nameYesPackage name within the repository, e.g. 'postgresql'.
repoYesRepository name on Artifact Hub (the 'repo' value from search_packages), e.g. 'bitnami'.
versionNoExact version. Omit for the latest version.
recent_versionsNoHow many recent versions to list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so safety is covered; the description adds substantive context on what actually comes back, including security-update flags, dependency and image data, and trust signals. The deliberate exclusion of readme text is a genuinely useful scope disclosure that prevents an agent from expecting content that will not appear. It stops short of noting response size, cost, or rate limiting for a tool that aggregates many sub-resources.

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?

Two sentences, front-loaded with the core purpose and then a dense but scannable inventory of returned fields; no filler or repeated boilerplate. The trailing note about the omitted readme is short and earns its place by setting a boundary.

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 must carry return-value information, and it does so thoroughly, listing every major section an agent will receive. The remaining gap is operational: nothing on result size, truncation of large version lists, or the cost of an open-world aggregation call.

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 kind, repo, name, version, and recent_versions are already well documented in the schema. The description only loosely gestures at parameters via 'latest plus recent releases with dates', which does not clarify that recent_versions controls list length or that omitting version selects latest. Baseline 3 applies when the schema carries the load.

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?

The opening clause 'One-call profile of a package' gives a specific verb-and-resource framing, and the enumerated contents (versions, vulnerabilities, maintainers, signing, trust flags) make the resource unambiguous. It does not name any sibling (e.g. security_report or changelog) as the narrower alternative, so differentiation is inferred from content overlap rather than stated.

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?

'One-call profile' implies you should reach for this instead of stitching together several narrower calls, which is a real, if implicit, usage cue. However, there is no explicit when-to-use/when-not-to-use guidance and no named alternative for agents that only need vulnerabilities (security_report) or version history (changelog).

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