Skip to main content
Glama
safe-ssh-mcp

safe-ssh-mcp

by Areso

get_ps_aux_top_mem_consumers

Lists the top 10 memory-consuming processes on a remote host over SSH, using ps aux sorted by memory and RSS fallback for BusyBox.

Instructions

Lists top 10 mem consumers, MEM desc (ps aux --sort=-%mem). On BusyBox hosts (Alpine), where ps cannot sort and has no %MEM, the output is ps -o pid,user,rss,vsz,args sorted by RSS instead: its first line starts with '# BusyBox' and sizes are in KB unless they carry an m or g suffix.

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_mem_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?

No annotations exist, so the description carries the full burden, and it does disclose genuine behavior: sort key, top-10 truncation, and a documented fallback path on Alpine/BusyBox with a different column set, RSS-based sorting, and KB units. It omits equally important behavior for a remote-execution tool — that it opens an SSH session, permission/auth requirements, timeout behavior, and whether it is read-only.

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: the primary behavior is front-loaded with the exact command, then the fallback case in a second sentence. Every clause (first-line marker, unit suffixes) is actionable detail for interpreting output, with no filler.

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, yet the description still earns its place by noting the output shape varies by host — a caveat the schema cannot express. What is missing is connection-oriented context (authentication options, timeout semantics, failure modes), which matters for a 7-parameter SSH-based tool.

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?

There are seven parameters at 0% schema description coverage, including security-relevant ones (key_path, password, accept_new_hostkey, timeout), and the description explains none of them. The only host-related remark concerns the remote OS's ps variant, not the `host` parameter itself, so it does not compensate for the coverage gap.

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 description gives a concrete verb and resource ('Lists top 10 mem consumers') and even names the underlying command (`ps aux --sort=-%mem`), which unambiguously separates it from the CPU-consumer sibling. It stops short of explicitly naming an alternative tool, so routing is implied by the memory focus 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 Guidelines2/5

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

It says what the tool returns but never states when to prefer it over nearby tools such as get_ps_aux_top_cpu_consumers, get_free_memory, or get_docker_stats, nor any prerequisites. The BusyBox paragraph explains output variance rather than when-to-use, leaving selection entirely to inference from the name.

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