Skip to main content
Glama

skein_user

Instance-wide user accounts. ADMIN ONLY — every action returns not_admin to a non-admin caller, before any database access. action="update" covers both the patch (name / role / password) and the deactivate / reactivate flip: deactivating cascades into API key revocation in the same transaction and is reversible with deactivated=false. Role admin is refused with admin_role_disabled while the instance admin role is disabled on the installation. action="space_add" makes the user a member of a space at once (no invitation, no consent). Read-only actions: list.

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": "skein_user"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoDisplay name (free-form, trimmed). Required for create; on update, omit to leave it unchanged.
roleNoRole of the account. Required for create; on update, omit to leave it unchanged. Demoting the last active admin returns `last_admin_cannot_demote`; a concurrent change after three attempts returns `concurrent_change` (retry).
emailNoUser email address. Must match a basic email regex; uniqueness is enforced on lower(email). Required for create.
limitNoOnly read by list: maximum rows to return, 1..100. Default 50.
spaceNoOnly read by space_add: short id of the space (skein_whoami lists the spaces).
actionYesWhat to do: - "list" → users of the instance, cursor-paginated, optionally filtered by `search`. - "create" → a new account; the user can sign in immediately with the supplied password. - "update" → patch name / role / password, or flip `deactivated`. - "space_add" → add `userId` to the space `space` at once.
cursorNoOnly read by list: opaque cursor token from a prior response's nextCursor.
searchNoOnly read by list: case-insensitive substring filter on email, username and name.
userIdNoUUID of the user to write to, as returned by list or create. Required for update and space_add.
archivedNoOnly read by list: list deactivated users instead of active ones. Default false.
passwordNoPassword, at least 8 characters. Required for create; on update, set it to reset the user's password. The user should rotate an admin-supplied password via POST /api/v1/me/password on first sign-in.
usernameNoDesired username (lowercase, 3..30 chars, [a-z0-9][a-z0-9_-]*). Only read by create; derived from the email local-part when omitted.
deactivatedNoOnly read by update: true → soft-deactivate (cascades into API key revocation), false → reactivate (does not un-revoke the previous keys). When set, name/role/password are ignored. Deactivating the last active admin returns `last_admin_cannot_demote`; a concurrent change after three attempts returns `concurrent_change` (retry).
is_externalNoOnly read by create: make the account an EXTERNAL collaborator. External users are visibility-scoped to their own projects and are permanently capped at role='user' — combining is_external=true with role='admin' is rejected (external_cannot_be_admin). Defaults to false (internal user). Set only at create time; there is no conversion path.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations: non-admin callers get `not_admin` before any database access, deactivation cascades into API key revocation inside the same transaction, reactivation does not un-revoke prior keys, and admin role is refused with `admin_role_disabled` while disabled. The disclosed irreversibility of key revocation is consistent with destructiveHint=false only because the account flip itself is reversible, and the description makes that distinction explicit rather than contradicting the 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-loads scope and the admin restriction in the first two clauses, then organizes the rest by action name, which makes it scannable. Some parenthetical nesting ("the patch (name / role / password)") and repeated error-code asides make it denser than strictly necessary.

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 complex, multi-action mutation tool with no output schema and no annotations describing side effects, the description covers authorization, transactional cascades, error codes, and reversibility well. It leaves the shape of returned data and list pagination to the schema, which is acceptable, but a brief note on what create/update returns would close the last gap.

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, but the description adds meaning the schema does not: action="update" merges patching name/role/password with the deactivate/reactivate flip, and space_add grants membership instantly with "no invitation, no consent." That framing of action semantics is genuinely additive for a 14-parameter tool.

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 the resource precisely ("Instance-wide user accounts") and enumerates the four actions with their effects, so an agent immediately knows this is the admin user-administration tool rather than a project/membership tool. The ADMIN ONLY framing and "Read-only actions: list" further pin the tool's identity.

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?

Explicitly signals the admin precondition and which action is safe to call (list), and explains what update and space_add do so the agent can pick the right action. It stops short of naming an alternative tool for related membership work (e.g. a project-members sibling), so routing between siblings is only implied.

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.