safe-ssh-mcp

Overview Schema Source Related Servers Discussions Admin

get_crictl_inspect_image

Inspect a specific image in a remote Kubernetes node’s CRI runtime over SSH, returning JSON details like tags, digests, size, user, entrypoint/CMD, layers, and redacted env values.

Instructions

Inspects a SPECIFIC image (crictl inspecti, JSON) in the CRI runtime of a kubernetes node from a remote Linux host via SSH: repo tags and digests, size, user, entrypoint/cmd, layers. image is an image name ('registry.k8s.io/pause:3.9') or an image ID from get_crictl_images. Usually requires root. Values of environment variables are replaced by ''; their names are kept.

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": {
      "image": "<image>",
      "host": "<host>",
      "user": "<user>"
    },
    "name": "get_crictl_inspect_image"
  }
}

Input Schema

Name	Required	Description	Default
`host`	Yes
`port`	No
`user`	Yes
`image`	Yes
`timeout`	No
`key_path`	No
`password`	No
`accept_new_hostkey`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.2.0Nov 13, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: execution happens remotely via SSH, root is typically needed, output is JSON in crictl inspecti form, and environment variable values are redacted while names are preserved. It leaves out the authentication modes (password vs key_path), host-key acceptance semantics, and timeout behavior, which are the remaining material gaps.

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?

The description is front-loaded with the action and target, then the concrete return fields, then the parameter hint and prerequisites. Every sentence carries information; nothing repeats the tool name or restates the title.

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?

An output schema exists, so the return-value details it lists are a bonus rather than a requirement, and the description still covers remote execution, privilege needs, and redaction. For an 8-parameter SSH tool with zero schema coverage and no annotations, the only shortfall is that connection/authentication parameters are not addressed at all.

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 0% across 8 parameters, so the description must compensate. It clarifies the most important one, 'image' (a name like 'registry.k8s.io/pause:3.9' or an ID retrieved from get_crictl_images), but leaves port, timeout, key_path, password, and accept_new_hostkey entirely unexplained in both schema and prose. Partial compensation only.

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?

The description names a specific verb and resource ('Inspects a SPECIFIC image ... in the CRI runtime of a kubernetes node') and enumerates the returned facts (repo tags and digests, size, user, entrypoint/cmd, layers). Capitalizing SPECIFIC plus grounding in 'crictl inspecti, JSON' distinguishes it from the list-style sibling get_crictl_images without requiring the agent to open another 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?

It gives concrete context for use (remote Linux host over SSH, CRI runtime on a k8s node), a prerequisite ('Usually requires root'), and routes the agent to get_crictl_images as the source of acceptable image IDs. It does not say when to prefer this over the sibling generic get_crictl_inspect, so there is a small routing gap.

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

Deploy Server