Skip to main content
Glama

Whitelist, operators, bans, and kicks

manage_access
Destructive

Manage Minecraft server access in one call: toggle and enforce the whitelist, add or remove operators, ban players and IPs, pardon bans, and kick online players with reasons.

Instructions

Change who may play, in one call; give only the parts you need. whitelist turns it on or off, enforces it (kicks online players who aren't on it), and adds or removes players. operators makes players operators or takes it away; it needs server:console, since an operator may run every command. ban bans players by name or UUID and banIps addresses, kicking anyone online they hit; pardon and pardonIps lift bans. kick disconnects players with a reason. Needs players:moderate. Confirm bans and kicks with the user first.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "manage_access"
  }
}

Input Schema

NameRequiredDescriptionDefault
banNoPlayers by name or UUID
kickNoOnline players to disconnect
banIpsNoIP addresses to ban
pardonNoPlayer names or UUIDs
operatorsNoNeeds server:console
pardonIpsNoIP addresses to unban
whitelistNoToggle, enforce, add, or remove

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv4.2.1
    • addedInput schema / properties / ban / description
      Added value: +"Players by name or UUID"
    • addedInput schema / properties / banIps / description
      Added value: +"IP addresses to ban"
    • addedInput schema / properties / kick / description
      Added value: +"Online players to disconnect"
    • addedInput schema / properties / operators / description
      Added value: +"Needs server:console"
    • addedInput schema / properties / pardonIps / description
      Added value: +"IP addresses to unban"
    • addedInput schema / properties / whitelist / description
      Added value: +"Toggle, enforce, add, or remove"
  2. First observedv4.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true, but the description goes well beyond them: enforcing the whitelist kicks non-whitelisted online players, bans kick anyone online they hit, operator grants carry elevated privilege risk, and bans/kicks need user confirmation. That is exactly the side-effect detail an agent needs before mutating server state.

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 one-line summary followed by semicolon-delimited per-operation clauses; every clause carries information. The density is high but readable, with only mild run-on risk in the whitelist clause.

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-parameter, nested, destructive tool with no output schema, the description covers each operation, permission requirements, and confirmation policy. It omits partial-failure/atomicity behavior (e.g., what happens if one ban in an array is invalid) and whether whitelist enforcement takes effect immediately.

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 real semantics per parameter group: ban accepts names or UUIDs, banIps takes addresses, pardon/pardonIps lift bans, kick disconnects with a reason, whitelist toggles/enforces/adds/removes. It does not clarify interaction between 'enabled' and 'enforced', which the schema leaves bare.

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 opening 'Change who may play, in one call' states the resource and the multi-operation batching model, then each clause names a concrete sub-operation (whitelist, operators, ban, banIps, pardon, pardonIps, kick). This clearly separates it from the read-only sibling get_access and from the generic run_command.

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?

'Give only the parts you need' tells the agent the tool is partial-update, and 'Confirm bans and kicks with the user first' is an explicit procedural precondition. Permission scoping is spelled out (server:console for operators, players:moderate otherwise). It stops short of naming alternatives such as get_access for reading current state.

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