Skip to main content
Glama

Run a server command

run_command
Destructive

Run Minecraft server commands via RCON and return the reply. Provide backup_area before commands that alter blocks so undo can restore the affected area.

Instructions

Runs any Minecraft server command through RCON and returns the reply, for example gamerule, time, weather, summon, give, op, reload, function, scoreboard, team, tp, data. Commands from mods and datapacks work too. Give backup_area to snapshot an area first so undo can put it back; otherwise this cannot be undone.

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": {
      "command": "<command>"
    },
    "name": "run_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandYesA server command without the leading slash, for example "time set day"
dimensionNoDimension to run the command in (and of backup_area). Default overworld.overworld
backup_areaNoArea this command may change; it is saved first so undo can restore it

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and non-idempotency, so the safety profile is known. The description adds value beyond that by tying backup_area to the undo tool and stating plainly that without it the effect cannot be reversed, and by noting mod/datapack commands are accepted. It omits whether the caller needs op-level permission or how failures are reported.

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 action and mechanism in the first clause, then the safety caveat last. The fourteen-command example list is longer than needed to convey breadth, but it does useful work showing the range of accepted commands.

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

Completeness5/5

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

Three parameters with a nested object and no output schema; the description covers the action, the mechanism, the breadth of accepted input, the return ('the reply'), and the irreversibility trade-off. An agent has everything needed to call it correctly and safely, with only op-permission expectations left implicit.

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 schema already documents command syntax (no leading slash), the dimension enum and its default, and the from/to coordinate arrays. The description's backup_area sentence largely restates the schema's own wording; the only addition is the consequence of omitting it, which is more behavioral than semantic. Baseline 3 is appropriate.

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 and resource (runs a Minecraft server command), the transport (RCON), and the return ('returns the reply'). The long example list (gamerule, time, summon, op, scoreboard, tp, data) plus 'commands from mods and datapacks work too' makes clear this is the general escape hatch rather than a narrow command type.

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 an explicit conditional: pass backup_area first if you may need to undo, otherwise the change is permanent. That is real when-to-do-what guidance. It stops short of routing the agent away from specialized siblings such as fill_blocks, place_blocks, or read_blocks when those would be the safer choice.

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