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

ssh_set_credentials

Destructive

Set login or sudo credentials for an SSH host so saved credentials are shared across clients; use temporary mode to override for this connection only.

Instructions

Set login or sudo credential, remembered by default and shared across clients. remember:false overlays it only for this MCP connection without deleting saved credentials. For sudo explicitly provide credential OR reuseSshPassword:true. Login credential changes require ssh_reset_connection for existing connections. Returns the latest host version; never returns secret values.

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>",
      "expectedVersion": "<expectedVersion>",
      "kind": "<kind>"
    },
    "name": "ssh_set_credentials"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
hostIdYesStable ID from ssh_list_hosts
rememberNo
credentialNoSSH password, private-key passphrase, or sudo password. Never echoed in results.
expectedVersionYesCurrent host version from ssh_list_hosts; stale writes return HOST_CONFLICT
reuseSshPasswordNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior5/5

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

The annotations already flag destructiveHint=true, idempotentHint=false, and openWorldHint=true, and the description adds substantial non-obvious context on top: credentials persist by default and are shared across clients, remember:false is a non-deleting overlay, sudo needs explicit credential or password reuse, and existing connections must be reset. It also closes the secret-handling question by stating secrets are never returned.

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?

Four dense sentences, each carrying a distinct fact (default persistence, overlay mode, sudo input rules, reset requirement, return value), with the core action front-loaded. There is little waste, though the sudo and reset clauses are packed tightly enough to require a careful read.

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?

For a destructive mutation tool with no output schema, the description covers the important unknowns: persistence, cross-client propagation, the required follow-up reset, and the return shape. It does not mention permission or authentication prerequisites, which is the main remaining gap for an openWorld, destructive operation.

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?

Schema coverage is only 50%, and the description compensates exactly where the schema is silent: it defines the semantics of remember:false, the either/or relationship between credential and reuseSshPassword, and the kind distinction between login and sudo. hostId and expectedVersion remain solely documented by the schema, which is acceptable since their schema descriptions are already precise.

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 opens with a specific verb and resource ("Set login or sudo credential") and immediately scopes the persistence behavior ("remembered by default and shared across clients"). It does not explicitly contrast itself with the similarly named ssh_set_workspace or other siblings, so it falls short of the 5 benchmark for sibling differentiation, but the purpose is unambiguous.

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 real operational context: use remember:false for a connection-scoped overlay, supply either a credential or reuseSshPassword:true for sudo, and call ssh_reset_connection after login credential changes on live connections. That is clear when-to-use and follow-up guidance, but there are no explicit exclusions or "do not use this if" conditions.

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