Skip to main content
Glama

Manage Remote Hosts

manage_remote_hosts
Destructive

Registers, lists, tests, and removes SSH hosts so security tools can run remotely instead of locally, with optional per-host tool allowlists.

Instructions

Add, list, test, or remove the SSH hosts that run_tool can target remotely.

Manages the remote-host registry that lets run_tool (and check_installed) run a tool on a remote Kali/Linux box over SSH instead of locally, so the tool only has to be installed on the remote. The action selects the operation: "list" shows every configured host; "add" registers or updates a host (needs name and hostname, plus optional user, port, ssh_key, and a tool_allowlist that restricts which tools may run there); "remove" deletes a host by name; "test" opens an SSH connection to confirm the host is reachable.

Connections use StrictHostKeyChecking=accept-new, so the key presented on the first connection is pinned in ~/.ssh/known_hosts and any later change is rejected. Verify that first fingerprint out-of-band for a host you do not control, or add the key to known_hosts before "test".

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": {
      "action": "<action>"
    },
    "name": "manage_remote_hosts"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoHost name (required for add/remove/test).
portNoSSH port (default 22).
userNoSSH username (default "kali").kali
actionYesOperation to perform: "list", "add", "remove", or "test".
ssh_keyNoPath to SSH private key (e.g. "~/.ssh/id_kali").
hostnameNoIP address or hostname of the remote machine (required for add).
descriptionNoHuman-readable description of the host.
tool_allowlistNoComma-separated list of allowed tool names (e.g. "nmap,gobuster,sqlmap"). None means all tools allowed.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.2.1
    • changedInput schema / properties / action / description
      Previous value: -"One of \"list\", \"add\", \"remove\", \"test\"."New value: +"Operation to perform: \"list\", \"add\", \"remove\", or \"test\"."
    • addedInput schema / properties / action / enum
      Added value: +[
      +  "list",
      +  "add",
      +  "remove",
      +  "test"
      +]
  2. First observedv1.2.0

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare destructive, non-idempotent, open-world behavior, and the description adds real value beyond that: the StrictHostKeyChecking=accept-new trust-on-first-use behavior, known_hosts pinning, fingerprint verification advice, and that tool_allowlist restricts which tools may run. It does not cover outcomes of edge cases such as removing an unknown host or a failed test, and "add" registers *or updates* sits slightly awkwardly against idempotentHint=false.

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?

Front-loads the operation list, then the registry's purpose, then the security caveat — a sensible order for an agent scanning quickly. Three paragraphs with little waste, though the action enumeration in the first line and the second paragraph overlap slightly.

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, so return values need not be described, and annotations cover the safety profile; the description fills the important gaps — SSH trust model, allowlist scope, and per-action requirements. Only edge-case behavior (nonexistent host on remove, what a failed test implies) is left unaddressed.

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 100%, so the schema alone justifies a 3; the description goes modestly beyond by tying parameters to actions (name required for add/remove/test, hostname required for add) and clarifying that tool_allowlist gates which tools may execute on that host. Most remaining parameter detail (defaults for port/user, ssh_key path format) is simply restated from 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?

Opens with a specific verb set and resource ("Add, list, test, or remove the SSH hosts") and ties it to a sibling ("that run_tool can target remotely"), so the registry's role is unambiguous. The follow-up sentence explains the effect on run_tool/check_installed, distinguishing it from every sibling in the list.

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 per-action guidance including prerequisites ("add" needs name and hostname, "remove" deletes by name, "test" confirms reachability) and names the tools it affects. It stops short of stating when not to use it or what to do if a host record already exists, so it is strong context without explicit exclusions.

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