Skip to main content
Glama

attack

Destructive

Attack another player, pirate, empire NPC, creature, station, or intact prize (target_id accepts a player ID, username, pirate ID, empire NPC ID, wildlife creature ID, intact-prize actor ID, or station/base ID. Target must be in the same system; an intact prize must also be at your current POI. Intact-prize actor IDs are listed by get_nearby; attacking one intercepts the physical captured hull during recovery. Attacking any target creates or joins a system-scale battle with zone-based tactical combat — it is not a single one-off volley. Once the battle exists it resolves automatically every tick without further commands. Do not re-issue 'attack' on a target you are already fighting: it never fires an extra volley — against a player already in your battle it merely re-points your target (identical to battle action 'target'), and against a pirate it re-applies the reputation penalty with that pirate faction and again summons every combat pirate in the system toward you. Reciprocal player attacks submitted for the same tick are each classified from tick-start state as independent aggression, so both attackers may receive crime, bounty, and reputation penalties. Use the 'battle' command with action parameter (advance, retreat, stance, target, engage, self_destruct) for tactical control. The attack response confirms the engagement only; read the fight through 'get_battle_status' (free, no battle_id needed — per-participant hull/shield plus your own damage_dealt and kill_count), the per-tick 'battle_damage' and 'battle_update' notifications, and 'get_battle_summary' for the final tally. Attacking a pirate NPC joins or creates the same shared system battle, and every other pirate combat hull in the system converges on you — it is not a 1v1. Killing one emits a 'pirate_destroyed' notification with credits_earned and, when a wreck is created, wreck_id plus its system and any POI you are allowed to see. Attacking an empire NPC triggers a battle and applies criminal status. Attacking a wildlife creature starts a hunt (equivalent to the 'hunt' command) — wildlife never dogpile, so engaging one creature does not pull in the rest of the herd. Opening fire on a station starts a siege against its hull, shields and gun batteries, which shoot back. Shelling an empire station is a serious crime — it costs three times the reputation that attacking one of its ships does, carries a bounty, and the police respond.)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
target_idYesID of the target: a player, pirate, empire NPC, wildlife creature, intact-prize actor, or station. Prize actor IDs come from get_nearby. Reciprocal player attacks submitted for the same tick are each classified from tick-start state as independent aggression, so both attackers may receive crime, bounty, and reputation penalties. Opening fire on a station starts a siege; shelling an empire station is a serious crime.
session_idYesYour session ID from login/register

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedInput schema / properties / target_id / description
      Previous value: -"ID of the target: a player, pirate, empire NPC, wildlife creature, intact-prize actor, or station. Prize actor IDs come from get_nearby. Opening fire on a station starts a siege; shelling an empire station is a serious crime."New value: +"ID of the target: a player, pirate, empire NPC, wildlife creature, intact-prize actor, or station. Prize actor IDs come from get_nearby. Reciprocal player attacks submitted for the same tick are each classified from tick-start state as independent aggression, so both attackers may receive crime, bounty, and reputation penalties. Opening fire on a station starts a siege; shelling an empire station is a serious crime."
  2. Changed1 schema field changed
    • changedInput schema / properties / target_id / description
      Previous value: -"ID of the target: a player, pirate, empire NPC, wildlife creature, or station. Opening fire on a station starts a siege; shelling an empire station is a serious crime."New value: +"ID of the target: a player, pirate, empire NPC, wildlife creature, intact-prize actor, or station. Prize actor IDs come from get_nearby. Opening fire on a station starts a siege; shelling an empire station is a serious crime."
  3. Changed1 schema field changed
    • changedInput schema / properties / target_id / description
      Previous value: -"Player ID to attack"New value: +"ID of the target: a player, pirate, empire NPC, wildlife creature, or station. Opening fire on a station starts a siege; shelling an empire station is a serious crime."
  4. First observed

TDQS

A4.9/5.0
Behavior5/5

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

The description goes far beyond the destructiveHint annotation, disclosing that combat is a system-scale auto-resolving battle, that repeated attacks have different effects on different target types, that player reciprocal attacks can cause crime/bounty/reputation penalties, that pirate attacks summon nearby pirates, that station attacks trigger sieges, and that empire station attacks carry heavy penalties. This is exactly the behavioral context an agent needs.

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?

The description is long but information-dense, with the core purpose front-loaded and nearly every clause carrying operational value. It loses a point for being structured as a dense block with some incidental repetition of pirate-convergence behavior and overlapping details with the input schema, but it remains well-organized enough to navigate.

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?

Given this tool's complexity and lack of an output schema, the description is remarkably complete: it covers valid targets, geographic constraints, combat model, response semantics, follow-up commands, per-target consequences, and crime/bounty implications. An agent has everything needed to invoke attack correctly and know what to expect afterward.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the schema already documents both parameters at 100% coverage, the description adds significant meaning: target_id accepts multiple ID categories, the target must be in the same system, intact-prize actor IDs come from get_nearby and must be at the current POI, and attacking an intact prize intercepts the physical hull. These constraints are not present in the schema and materially affect correct invocation.

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 description opens with a specific verb and resource: 'Attack another player, pirate, empire NPC, creature, station, or intact prize.' It enumerates the full set of valid target types and clearly distinguishes this command from related combat tools like 'battle' and 'hunt' by explaining what each does.

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?

The description gives explicit when-to-use guidance: attack initiates combat, while 'battle' provides tactical control; attacking wildlife is equivalent to 'hunt'; and users should not re-issue 'attack' on an already-engaged target because it will not fire an extra volley. It also explains when to read results via get_battle_status and get_battle_summary, making alternatives and exclusions explicit.

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.

TDQS

B3.4/5.0
Disambiguation4/5

Most tools are clearly distinct, targeting specific actions and resources. A few overlaps exist (e.g., attack vs hunt, view_insurance vs claim_insurance), but detailed descriptions clarify the boundaries. The scale makes selection harder, but each tool has a clear purpose.

Naming Consistency4/5

The majority use a consistent verb_noun snake_case pattern (e.g., create_buy_order, get_cargo, accept_mission). There are minor deviations like action-dispatch commands (facility, shipping, citizenship) and bare verbs (attack, dock, mine), but these are readable and follow a logical style.

Tool Count1/5

With 212 tools, the server far exceeds any reasonable scope for an MCP. While the game is complex, this is an extreme number that overwhelms agents and users, making discovery and selection impractical. The calibration considers 25+ already too many, and 212 is extreme.

Completeness5/5

The toolset covers nearly every aspect of the game: combat, trading, crafting, factions, missions, exploration, drones, passengers, freight, insurance, taxation, and more. It provides full CRUD for most resources and includes both action and query tools, leaving few obvious gaps.

Resources