Skip to main content
Glama

Get a challenge to prove an SSH key is yours

ssh_key_challenge

Issue a one-time signing challenge so a person can prove ownership of an SSH key locally before its public half is registered for connection.

Instructions

Issue a challenge to sign with the private half of a key about to be added, so add_ssh_key registers it as proven: a proven key connects to a computer by id or by name, an unproven one by id only. The answer carries the challenge, its namespace, when it expires, and sign_command: a shell command the PERSON runs on their own machine, replacing the key file it names with their private key file. Never ask for or handle the private key yourself. Send the challenge and the signature it prints to add_ssh_key. A challenge is not a credential: it belongs to this person alone, works once, expires within minutes, and asking for more than eight at once drops the oldest. Refused (403) where adding a key is: a key confined to a workspace, one that expires or is limited to computers, or a holder whose email is not verified.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "ssh_key_challenge"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.23.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: the challenge is single-use, person-bound, expires in minutes, and is rate-limited at eight with oldest-dropped behavior. It also lists the exact refusal cases (workspace-confined key, expiring/computer-limited key, unverified email) and warns the private key must never be handled by the agent.

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?

The critical instruction (issue a challenge, send it to add_ssh_key, never handle the private key) is front-loaded, and each sentence adds distinct information. It is dense and long, and the aside about proven keys connecting by id or name is somewhat marginal, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, no-output-schema, no-annotation tool, the description covers everything an agent needs: invocation purpose, the downstream handoff, the shape of the return value, rate limits, expiry, and failure modes. Nothing material is missing.

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?

The tool takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. The description instead usefully documents the response payload (challenge, namespace, expiry, sign_command), which the absent output schema would otherwise leave undocumented.

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?

The description names a specific verb and resource ('Issue a challenge to sign with the private half of a key') and ties it directly to the sibling tool it feeds, add_ssh_key. An agent can distinguish this from add_ssh_key or list_ssh_keys without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states exactly when to call it (a key is about to be added), what to do with the result (send the challenge and signature to add_ssh_key), and an explicit exclusion ('Never ask for or handle the private key yourself'). The 403 refusal conditions further scope when the call will fail.

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

Deploy Server

Other Tools