Skip to main content
Glama

Which base images in this Dockerfile are out of support?

Which base images in this Dockerfile are out of support?

check_dockerfile
Read-only

Paste a whole Dockerfile. Returns every FROM line whose base image is a Python, Node.js or Ubuntu release this register holds, with that release's end-of-active-support and end-of-security-support dates, whether it is past either one today, and a verbatim quote of the vendor's own published line. Every FROM line it could NOT answer for — another product, a latest or build-argument tag, a bare digest, an earlier build stage — comes back in not_in_our_records or unresolvable with the reason in words, and is counted in images_unresolved. An empty out_of_support list with a non-zero images_unresolved does NOT mean the file is clean.

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": {
      "dockerfile": "<dockerfile>"
    },
    "name": "check_dockerfile"
  }
}

Input Schema

NameRequiredDescriptionDefault
dockerfileYesThe Dockerfile text. Multi-stage files, `--platform` flags, `AS` stage names, comments, registry prefixes and digest pins are all handled; nothing else in the file is read.

Output Schema

NameRequiredDescriptionDefault
verdictYesOne sentence. Always says how many lines were not checked.
coverageYes
registerNo
supportedNoChecked images inside both windows.
from_linesYesFROM lines found in the file.
unresolvableYesFROM lines this tool could not answer for. Read this before reporting a Dockerfile clean: these lines were NOT checked, which is not the same as being in support.
images_checkedYesFROM lines matched to a release in this register.
out_of_supportYesChecked images past end of security support, soonest-expired first.
images_unresolvedYesFROM lines not checked. See not_in_our_records and unresolvable.
not_in_our_recordsYesFROM lines this tool could not answer for. Read this before reporting a Dockerfile clean: these lines were NOT checked, which is not the same as being in support.
past_active_supportNoChecked images still getting security fixes but no longer bug fixes.

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?

Annotations only say read-only and closed-world; the description adds the real behavior: which fields come back (end-of-active-support, end-of-security-support, vendor quote), how unanswerable FROM lines are bucketed with reasons, and the critical warning that an empty out_of_support plus non-zero images_unresolved is not a clean result.

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 action and kept to three dense sentences with no filler; the closing caveat is high-value. The middle sentence is long and comma-heavy, which slightly taxes scanning.

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 one-parameter, read-only file scanner with an output schema, this covers purpose, result shape, failure modes, and a misinterpretation trap. Nothing an agent needs to call it correctly and read the result safely 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?

The schema already documents the single parameter at full coverage, including multi-stage/--platform/digest handling, so it does most of the work. The description still adds meaning by framing the input as an entire file rather than a snippet and by enumerating which tag forms (latest, build args, bare digests, earlier stages) yield unresolvable output.

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 concrete verb and resource: 'Paste a whole Dockerfile. Returns every FROM line whose base image is a Python, Node.js or Ubuntu release this register holds.' The whole-file scope plus the named product coverage makes it clearly distinct from a per-release lookup like release_support_status.

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?

The input contract ('paste a whole Dockerfile') establishes when this tool applies, and the note about what lands in not_in_our_records/unresolvable tells the agent when results are untrustworthy. It stops short of naming the sibling tool or an explicit when-not-to-use case.

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