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

ssh_forget_host_key

Destructive

Forget a host endpoint's trusted SSH fingerprint after verifying its identity so the next fresh connection records a new fingerprint; existing connections stay unchanged.

Instructions

Explicitly forget this host endpoint's trusted SSH fingerprint after independently verifying its identity. Next fresh connection records a new fingerprint. Existing connections are not retroactively reverified; reset them explicitly. Never use automatically to bypass a fingerprint mismatch.

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>"
    },
    "name": "ssh_forget_host_key"
  }
}

Input Schema

NameRequiredDescriptionDefault
hostIdYesStable ID from ssh_list_hosts
expectedVersionYesCurrent host version from ssh_list_hosts; stale writes return HOST_CONFLICT

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and non-idempotency, but the description goes beyond them by explaining the actual consequence (the next fresh connection records a new fingerprint) and the scope limit (existing connections are unaffected and must be reset separately). This is the behavioral context an agent needs to avoid assuming an immediate global effect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with what the tool does, then consequences, then the misuse warning. No filler, and each sentence carries distinct operational or safety information.

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, non-idempotent mutation with no output schema, the description covers effect, scope, precondition, and misuse conditions well. It does not address required permissions/authorization or what a successful response looks like, minor gaps given the annotations and fully documented schema.

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 description coverage is 100%: hostId and expectedVersion are both fully documented, including the HOST_CONFLICT outcome for stale versions. The description mentions neither parameter, so it adds no meaning beyond the schema; baseline 3 applies.

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?

"Explicitly forget this host endpoint's trusted SSH fingerprint" states a precise verb (forget) and a precise resource (the host's trusted SSH fingerprint), which separates it from sibling mutations like ssh_update_host or ssh_set_credentials. The added note that existing connections are not retroactively reverified further distinguishes it from ssh_reset_connection, so an agent can route correctly without opening schemas.

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 a clear precondition ("after independently verifying its identity") and an explicit prohibition ("Never use automatically to bypass a fingerprint mismatch"), which is exactly the safety guidance needed for a destructive trust operation. It also hints at the remediation path ("reset them explicitly") without naming the sibling tool by name, so the alternative is implied rather than spelled out.

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