Skip to main content
Glama

FrontierStack by Enfour, Inc.

Ask the owner to replace a stored credential

replace_credential
Destructive

Ask the owner to type a new value for one of the selected Mac’s stored credentials (an API key or token FrontierStack keeps, such as openai, anthropic, cloudflare or stripe) on a secure FrontierStack page, for example after a key has leaked. The value goes from the owner’s browser straight to the Mac, sealed to it and confirmed with a passkey the Mac created; it never passes through the AI client or the conversation, and this tool neither accepts nor returns it. The first call returns a link for the owner (a URL elicitation where the client supports it) with a short code they can compare; a repeat call with the same arguments returns the outcome once they have finished. Requires web approvals and credential entry to be turned on for that Mac.

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": {
      "service": "<service>"
    },
    "name": "replace_credential"
  }
}

Input Schema

NameRequiredDescriptionDefault
mac_idNoOpaque id of one of this account's FrontierStack Macs. Optional only when exactly one Mac is online.
reasonNoWhy, in a few words, shown to the owner on the page (for example "the key was pasted into a chat").
serviceYesThe credential to replace: its FrontierStack id (for example openai, anthropic, cloudflare, stripe, github) or the service name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / mac_id / description
      Previous value: -"Opaque Mac id returned by list_frontierstack_macs. Optional only when exactly one Mac is online."New value: +"Opaque id of one of this account's FrontierStack Macs. Optional only when exactly one Mac is online."
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

With annotations already flagging destructiveHint=true, the description adds substantial non-obvious behavior: the secret never traverses the AI client or conversation, flows browser-to-Mac sealed with a passkey, and the tool neither accepts nor returns the value. It also clarifies the two-phase elicitation flow and the short-code verification, which is far beyond what annotations convey. The repeat-call outcome note sits alongside idempotentHint=false without actually contradicting it, since no new replacement is implied.

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?

Three dense sentences that front-load the action and then layer security model and call flow; nothing is wasted, but the middle sentence is long and could be split for faster scanning. Structurally sound overall.

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?

Despite having no output schema, the description explains exactly what an agent gets back: a link (or URL elicitation) plus a short code on the first call and the final outcome on a repeat call. Combined with the prerequisite and security disclosure, an agent has everything needed to invoke it correctly.

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 every parameter's meaning (mac_id optionality when a single Mac is online, reason shown to the owner, service id or name) is already documented in the schema. The description reinforces the owner-facing nature of the page but adds no syntax or format detail beyond the structured fields, so 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?

The description names a specific verb and resource — "Ask the owner to type a new value for one of the selected Mac's stored credentials" — and scopes it to an enumerated set of secrets (API keys/tokens such as openai, anthropic, cloudflare, stripe). This is clearly distinguishable from siblings like service_action or diagnose, which operate on the Mac/service rather than on stored secrets.

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 an explicit triggering context ("for example after a key has leaked") and states the prerequisite that web approvals and credential entry must be turned on for that Mac. It also explains the two-call pattern (first call yields a link, repeat call with same arguments yields the outcome). No explicit when-not or named alternative tool is given, which keeps it below a 5.

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.