AI agents invoke heal to trigger actions in MCP Arena. 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.
The heal tool triggers an in-game action (consuming a healing potion) that modifies the agent's game state (HP restoration) within a live match. It is an action with external side effects on the game session, fitting Execute. It is not purely a data write/read, and while reversible in a game sense, the potion use is consumed (limited to 2 per match), making it a stateful game action.
From the tool's definition Usar pocion de curacion. Restaura 30% del HP maximo. Maximo 2 usos por partida.
Attacks that exploit this kind of access
Usar pocion de curacion. Restaura 30% del HP maximo. Maximo 2 usos por partida. It is categorised as a Execute tool in the MCP Arena MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Arena MCP server in PolicyLayer and add a rule for heal: 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 MCP Arena. Nothing to install.
heal 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 heal 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 heal. 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.
heal is provided by the MCP Arena MCP server (jerick97/mcp-arena). 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 →