Skip to main content
Glama

Keychain secret

crbro_secret
Destructive

Store and retrieve credentials in the local OS keychain so secrets stay out of AI memory and sync. Overwrites and removals require a confirmation token.

Instructions

Read or write credentials in the OS keychain (macOS Keychain, Linux Secret Service, Windows DPAPI); no sync or team space reaches it. When the user hands you a credential, set it, then crbro_learn only the NAME. get returns value and source: never print it unless asked; missing = found:false. Environment variables count only as CRBRO_SECRET_ or when listed in CRBRO_SECRET_ENV. Overwriting with a different value, and remove, are two-step: the first call changes nothing and returns confirm_token; show the user, get agreement, call again with confirm. A missing store file is an error, never empty; on Windows crbro-memory secret restore puts back a sealed copy.

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": "crbro_secret"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoSCREAMING_SNAKE_CASE, e.g. WORDPRESS_APP_PASSWORD. For get, set, remove.
valueNoThe credential, non-empty. Only for set.
actionYesget one, set (store or update) one, list names only, remove one, status = which keychain this machine offers.
confirmNoconfirm_token from the first call of an overwrite or remove.
descriptionNoWhat it is for. Only for set.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv2.12.0
    • changedInput schema / properties / action / description
      Previous value: -"get = read one, set = store or update one, list = names only, remove = delete one, status = which keychain this machine offers, or why none."New value: +"get one, set (store or update) one, list names only, remove one, status = which keychain this machine offers."
    • addedInput schema / properties / confirm
      Added value: +{
      +  "description": "confirm_token from the first call of an overwrite or remove.",
      +  "type": "string"
      +}
    • changedInput schema / properties / description / description
      Previous value: -"What it is for, e.g. \"WordPress example.com - REST API\". Only for set."New value: +"What it is for. Only for set."
    • changedInput schema / properties / name / description
      Previous value: -"SCREAMING_SNAKE_CASE, e.g. WORDPRESS_APP_PASSWORD. Required for get, set and remove."New value: +"SCREAMING_SNAKE_CASE, e.g. WORDPRESS_APP_PASSWORD. For get, set, remove."
    • changedInput schema / properties / value / description
      Previous value: -"The credential itself, non-empty. Only for set."New value: +"The credential, non-empty. Only for set."
  2. Changed1 schema field changedv2.4.0
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
  3. Addedv1.14.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and non-idempotent, but the description adds the essential detail they don't: overwrite and remove are two-step via a confirm_token and the first call changes nothing. It also discloses 'missing = found:false', that env vars count only as CRBRO_SECRET_<NAME> or those in CRBRO_SECRET_ENV, that a missing store file is an error rather than empty, and the Windows restore escape hatch.

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-loaded with what it is, then rules in descending priority; every clause carries operational meaning. It is dense and telegraphic (semicolon-chained), which slightly taxes parsing but wastes little.

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 compensates by explaining get's return (value and source) and the found:false case, plus error behavior for a missing store file. list and status return shapes remain unstated, and the env-var precedence relative to the keychain is implicit.

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 baseline is 3; the description earns extra by explaining the two-step confirm_token lifecycle that ties `confirm` to a prior call, which the schema only hints at. Value/description scoping to set and name usage across get/set/remove are largely 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?

States a specific verb+resource ('Read or write credentials in the OS keychain') and scopes it precisely (macOS Keychain, Linux Secret Service, Windows DPAPI) with the boundary that no sync or team space reaches it. Governs five actions and names crbro_learn as the companion tool for the name, so it is distinguishable from flush storage siblings.

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 a concrete trigger: 'When the user hands you a credential, set it, then crbro_learn only the NAME', and routes the name elsewhere. Also states get-behavior and the confirm precondition for overwrite/remove. Lacks an explicit 'when not to use' against crbro_share/crbro_recall for credential-adjacent cases.

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