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

ssh_add_host

Destructive

Persist a new uniquely named SSH host shared by Codex and Claude, storing password or key credentials for later remote sessions. Returns a stable host ID and version.

Instructions

Persist a new uniquely named SSH host shared by Codex and Claude. For password auth provide credential; for key auth provide privateKeyPath and optional credential passphrase. Credentials are remembered by default; remember:false uses this MCP connection only. Returns stable ID and version. No interactive dialog.

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": {
      "name": "<name>",
      "hostname": "<hostname>",
      "username": "<username>",
      "auth": "<auth>"
    },
    "name": "ssh_add_host"
  }
}

Input Schema

NameRequiredDescriptionDefault
authYes
nameYes
portNo
hostnameYes
rememberNo
usernameYes
credentialNoSSH password, private-key passphrase, or sudo password. Never echoed in results.
jumpHostIdNo
privateKeyPathNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare the write/destructive/open-world profile, so the description's job is to add context, and it does: credentials persist by default, remember:false scopes them to this MCP connection only, the call returns a stable ID and version, and there is no interactive dialog. Those are real behavioral facts an agent could not infer from the annotations. It omits failure modes (duplicate name, unreachable host) and any permission prerequisites.

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?

Five short, front-loaded sentences with no filler; the auth branching and persistence semantics come before the return-value note. 'No interactive dialog' is slightly tangential but does preempt a real agent question about prompting.

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?

With no output schema, the description supplies the return shape ('stable ID and version'), and annotations cover the safety profile. The remaining gap is the undocumented jumpHostId/port parameters and no statement of what happens on duplicate names, which matters for a non-idempotent create.

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 only 11%, so the description must carry the load, and it explains auth, credential, privateKeyPath, and remember well. But jumpHostId and port are undocumented anywhere, and the interaction between credential (password vs passphrase) and auth is only partially spelled out. It compensates for roughly half 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 opens with a specific verb+resource: 'Persist a new uniquely named SSH host shared by Codex and Claude.' The word 'new' plus the uniqueness constraint distinguishes it from the sibling ssh_update_host without naming it. It stops short of an explicit sibling contrast, so it lands just under a 5.

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?

It gives conditional guidance for the two auth modes ('For password auth provide credential; for key auth provide privateKeyPath'), which is useful branch selection. However, it never says when to choose this tool over ssh_update_host or ssh_set_credentials, nor what happens if the host already exists. Usage is implied rather than delimited.

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