Skip to main content
Glama
remote-ssh-mcp
by RuiFG

ssh_test_connection

Destructive

Test SSH and SFTP access using a temporary connection without altering the active workspace or working SSH session; missing credentials fail immediately and can be set with ssh_set_credentials.

Instructions

Test SSH and SFTP with a temporary connection. Does not change this MCP connection's workspace or working SSH connection. Missing credentials fail immediately; set them with ssh_set_credentials.

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": {
      "hostId": "<hostId>"
    },
    "name": "ssh_test_connection"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostIdYesStable ID from ssh_list_hosts

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.1/5.0
Behavior4/5

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

Adds real value beyond the annotations by promising that this 'temporary connection' does not alter the MCP session's workspace or active SSH connection, and by disclosing fail-fast behavior on missing credentials. The one unexplained trait is destructiveHint=true — for a 'test' tool the agent is left wondering what could actually be destroyed (plausibly host-key trust entries), which is a meaningful residual gap.

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?

Three short sentences, front-loaded with the action, then the side-effect scoping, then the failure/credential remedy. No filler or restated naming.

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?

There is no output schema, and the description never indicates what the test reports (e.g. separate SSH vs SFTP results, auth errors, host-key prompts), which is the key information an agent needs to interpret the call. Combined with the unexplained destructive hint, the definition is adequate for invocation but incomplete for interpretation.

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% and the hostId field already explains it as a 'Stable ID from ssh_list_hosts' with UUID format and pattern. The description adds nothing about hostId, which is acceptable given the schema does the work, but means no extra meaning is contributed.

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 specific verb and resource ('Test SSH and SFTP with a temporary connection') and immediately scopes it as non-persistent, which cleanly separates it from siblings like ssh_shell_exec, ssh_set_connection or ssh_add_host. An agent knows exactly what operation this performs without opening the 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?

Gives a clear precondition and routing instruction: missing credentials fail immediately, so call ssh_set_credentials first. It does not explicitly say when to prefer this over actually executing a command via ssh_shell_exec (e.g. as a pre-flight validation step), so full when/when-not coverage is absent.

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