Skip to main content
Glama
takleb3rry

Zitadel MCP

by takleb3rry

zitadel_offboard_user

DestructiveIdempotent

Offboard a Zitadel user by removing project role assignments, revoking org-manager grants, and deactivating the account. Includes safeguards against removing the last admin or owner.

Instructions

Offboard a user: remove their Admin|Standard project role assignment, revoke any org-manager grant, and deactivate the account. Guards: cannot remove the last Admin, cannot self-demote (pass actingUserId), cannot remove the last ORG_OWNER. Requires confirm: true.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
emailNoEmail of the user to offboard (used if userId omitted)
userIdNoThe Zitadel user ID to offboard (or provide email)
confirmNoMust be true to execute. Omit to preview the action.
projectIdNoProject ID (uses default project if omitted)
deactivateNoDeactivate the account (default: true)
actingUserIdNoThe user performing the action — blocks self-demotion if it equals the target
removeManagerNoRevoke org-manager grant (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0

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 idempotentHint=true, yet the description still adds substantive context beyond them: the exact set of mutations performed, the last-Admin/ORG_OWNER protection rules, and the confirm-gated preview mode. That is exactly the elevated bar annotations should not count toward.

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?

Dense but front-loaded: the offboard action leads, the guards are compressed into one clause-heavy sentence, and the confirm requirement is stated last where it is most likely to be acted on. No filler sentences, though the semicolon-heavy guards take a second read.

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 7-param mutation with full schema coverage and no output schema, the description covers the action, the guards, and the preview/confirm protocol adequately. It stops short of describing reversibility or what happens to other grants the user may hold, which would matter for an offboarding operation.

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 baseline is 3, but the description adds genuine meaning: it explains why actingUserId exists (self-demotion block), what confirm does beyond 'must be true' (omitting previews), and names the role removals tied to removeManager. It does not cover projectId or deactivate defaults, so not a 5.

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 (offboard) plus the concrete sub-actions it performs (remove Admin|Standard project role, revoke org-manager grant, deactivate account), which distinguishes it from siblings like zitadel_deactivate_user and zitadel_delete_user that do only one of those things.

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 explicit preconditions and exclusions: 'Requires confirm: true', 'Omit to preview', and three hard guards (last Admin, self-demotion, last ORG_OWNER). It doesn't explicitly route to a sibling for partial operations, but the guard conditions clearly scope when this tool may be used.

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