Skip to main content
Glama

Rescue SSH password login

vps_rescue_password_auth
Destructive

Hypervisor-mediated rescue: when SSH is unreachable, generate a fresh key via the guest agent, SSH in, enable PasswordAuthentication in sshd_config (including drop-in overrides), and store the key for future web terminal access. Pass enabled=false to clear the hypervisor rootPasswordLogin flag instead.

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": {
      "id": "<id>",
      "enabled": "<enabled>"
    },
    "name": "vps_rescue_password_auth"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe VPS ID
enabledYesWhether to enable PasswordAuthentication. false = clear the hypervisor rootPasswordLogin flag.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and destructiveHint=true; the description goes further by disclosing the mechanism, that sshd_config drop-in overrides are also modified, and that a key is persisted for future web terminal access (a lasting credential side effect). It does not say what happens if the guest agent is unavailable or whether the change can be undone, which keeps it from a 5.

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?

Two sentences, front-loaded with the rescue condition and then the step sequence, with the inverse case last. The first sentence is dense but every clause carries operational information; 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?

For a multi-step, destructive rescue procedure the description covers the full workflow and its persistence side effect, and no output schema exists so return values need not be explained. The remaining gap is that it never says whether the newly generated key is returned to the caller or only stored.

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 coverage is 100% and the enabled parameter's schema description already states that false clears the hypervisor rootPasswordLogin flag, so the description largely restates it. The only added nuance is the 'including drop-in overrides' scope for the enabled=true path, which is marginal beyond the schema.

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 compound action (generate key via guest agent, SSH in, enable PasswordAuthentication, store key) and scopes it to the 'SSH is unreachable' rescue case. The 'Hypervisor-mediated rescue' framing plus the guest-agent detail separates it from a plain sshd-config toggle like vps_set_password_auth without needing to name it.

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?

The trigger condition is explicit ('when SSH is unreachable'), and the final sentence routes the opposite intent to the enabled=false path. It stops short of naming an alternative sibling (e.g. the non-rescue password-auth setter) for the normal reachable case, so the agent must infer the boundary.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.