Skip to main content
Glama

Manage saved logins

manage_logins
Destructive

Save, change or delete a saved login: URL, username, password and notes, encrypted at rest. The password is never echoed back. To read a password use reveal_values item login; to list logins use list_project_items item logins. An API key with no sign-in page belongs in manage_secrets. Actions (arguments besides action and project):

  • create (password; optional name, url, username, notes): adds one even under a name in use; name defaults to one made from the URL.

  • update (login; at least one of the same five fields): changes only the fields passed.

  • delete (login): removes it permanently. login is the id, or the exact name if no other login shares it. Every action returns the login's id and name, never the password; update adds changed (the fields it changed) and delete adds deleted: true. Errors are messages: a protected or archived project, a protected or sealed login, a name that matches nothing or several logins. Audited. Needs logins:write and the editor role.

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>",
      "project": "<project>"
    },
    "name": "manage_logins"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoSign-in page URL
nameNoShown in lists; derived from the URL when omitted
loginNoupdate, delete: login id, or its exact name
notesNoFree-text notes, up to 16 KB, encrypted like the password
actionYesWhat to do
projectYesProject slug from list_projects, e.g. my-app, or its id (a UUID)
passwordNocreate: required password, up to 4096 characters. update: the new password
usernameNoUsername or email used to sign in

Output Schema

NameRequiredDescriptionDefault
idNocreate, update, delete: the login id
nameNocreate, update, delete: the login's name
changedNoupdate: which parts changed (url, name, username, password, notes, sealed, ...)
deletedNodelete: true once the login is gone

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "https://json-schema.org/draft/2020-12/schema",
      +  "additionalProperties": {},
      +  "properties": {
      +    "changed": {
      +      "description": "update: which parts changed (url, name, username, password, notes, sealed, ...)",
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "deleted": {
      +      "description": "delete: true once the login is gone",
      +      "type": "boolean"
      +    },
      +    "id": {
      +      "description": "create, update, delete: the login id",
      +      "type": "string"
      +    },
      +    "name": {
      +      "description": "create, update, delete: the login's name",
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
      -  "create",
      -  "update"
      -]New value: +[
      +  "create",
      +  "update",
      +  "delete"
      +]
    • changedInput schema / properties / login / description
      Previous value: -"update only: login id, or its exact name"New value: +"update, delete: login id, or its exact name"
  3. Changed1 schema field changed
    • changedInput schema / properties / project / description
      Previous value: -"Project slug or id"New value: +"Project slug from list_projects, e.g. my-app, or its id (a UUID)"
  4. Added

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's main job is the extra context, which it delivers: password never echoed, encrypted at rest, create adds duplicates even under an existing name, update patches only passed fields, delete is permanent, plus audited access and required scopes (logins:write, editor role). Naming the error classes (protected/archived project, protected/sealed login, ambiguous or non-matching name) is exactly the kind of behavior annotations cannot express. A 3 reflects that this context is present and useful but the safety profile itself is already carried by annotations.

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 the core purpose and sibling routing, then a compact per-action bullet list. Dense but nearly every clause carries operational information; the only mild cost is length from stacking routing, per-action arguments, return shapes and error classes in a single block.

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

Completeness3/5

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

For an 8-parameter destructive mutation tool it covers prerequisites, per-action arguments, return shape and failure modes well, and an output schema exists so return values need not be spelled out. The gaps are minor: the description does not say whether delete is reversible or how name collisions interact with the id-vs-name resolution rule on later calls.

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%, so the baseline is 3. The description does add cross-field meaning the schema lacks (which fields each action accepts, update requiring at least one of five fields, and the rule that login is the id or the exact name only when unambiguous), which is a modest lift above the baseline.

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 set and resource: "Save, change or delete a saved login: URL, username, password and notes, encrypted at rest." The first sentence alone lets an agent separate this from reveal_values, list_project_items and manage_secrets, which are named explicitly later.

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?

Explicitly routes to alternatives with conditions: read a password -> reveal_values, list logins -> list_project_items, API keys with no sign-in page -> manage_secrets. Each action also carries its own required arguments and constraints, leaving little to inference.

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.

Resources