Skip to main content
Glama
safe-ssh-mcp

safe-ssh-mcp

by Areso

get_ps_aux_top_cpu_consumers

Retrieve the top 10 CPU-consuming processes on a remote SSH host; automatically falls back to top -b -n 1 output on BusyBox/Alpine systems where ps aux cannot sort.

Instructions

Lists top 10 cpu consumers, CPU desc (ps aux --sort=-%cpu). On BusyBox hosts (Alpine), where ps cannot sort, the output comes from top -b -n 1 instead: its first line starts with '# BusyBox', the columns differ, and %CPU is the usage at this moment, not the average over the process lifetime that ps reports.

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": {
      "host": "<host>",
      "user": "<user>"
    },
    "name": "get_ps_aux_top_cpu_consumers"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostYes
portNo
userYes
timeoutNo
key_pathNo
passwordNo
accept_new_hostkeyNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.14

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose real behavioral traits: the BusyBox fallback to `top -b -n 1`, a detectable marker line ('# BusyBox'), differing columns, and a semantic difference in %CPU (instantaneous vs lifetime average). What it omits is equally behavioral: it requires remote SSH authentication and is silent on connection failure, timeouts, or permission requirements.

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?

Three sentences, front-loaded with what the tool returns, followed by the conditional caveat. Every clause carries information; the BusyBox detail is verbose but materially affects result interpretation, so it earns its place.

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

Completeness3/5

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

An output schema exists, so return values needn't be described, and the description goes further by explaining output-shape divergence per host type. Against that, a 7-parameter SSH-based tool with 0% schema coverage and no annotations leaves authentication, connection, and safety semantics entirely undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 7 parameters, and the description mentions none of them. Nothing explains what `host`/`user` address, what `accept_new_hostkey` does (a security-relevant default of false), or how `key_path`/`password` interact, so the agent must guess at credential handling.

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?

States a specific verb and resource ('Lists top 10 cpu consumers') and grounds it in the exact command (`ps aux --sort=-%cpu`), which separates it from the sibling `get_ps_aux_top_mem_consumers` by resource. It stops short of an explicit contrast with that sibling, so differentiation is inferred from the word 'cpu' 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?

The BusyBox paragraph effectively tells the agent when the tool's output will look different (Alpine/alpine hosts where ps cannot sort), which is useful conditional context. However, there is no explicit when-to-use/when-not guidance against alternatives, and no prerequisites such as needing SSH access or valid credentials.

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