Execute an attack in the current battle. The attacker must be the Pokemon whose turn it is (determined by speed on turn 1, then alternating). Returns damage dealt, effectiveness, and updated HP for both Pokemon. If the defender faints, the battle ends.
AI agents invoke attack to trigger actions in Pokemon MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes a game action whose outcome depends on arguments and internal state rather than just retrieving data. While the effects are confined to a simulated Pokemon battle system (limited blast radius), the tool triggers external logic that modifies battle state irreversibly within that session. It does not permanently delete data or move money, so Destructive and Financial are ruled out.
From the tool's definition Tool description states it 'Execute[s] an attack in the current battle' with effects that are 'determined by' game state (speed, turn order) and produces 'updated HP' and potential battle termination ('defender faints, the battle ends').
Attacks that exploit this kind of access
Execute an attack in the current battle. The attacker must be the Pokemon whose turn it is (determined by speed on turn 1, then alternating). Returns damage dealt, effectiveness, and updated HP for both Pokemon. If the defender faints, the battle ends. It is categorised as a Execute tool in the Pokemon MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pokemon MCP Server MCP server in PolicyLayer and add a rule for attack: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Pokemon MCP Server. Nothing to install.
attack is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the attack rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for attack. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
attack is provided by the Pokemon MCP Server MCP server (thesidshah/pokemon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →