AI agents invoke move 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.
This tool executes a game action (moving on a grid) within a turn-based combat platform. It causes a state change in the game environment (position update), making it Execute rather than Write, as it triggers an external operation in a live arena match. The blast radius is low since it only affects game state within a sandboxed combat session.
From the tool's definition 'Mover en la grilla 20x14. Solo en tu turno.' — triggers a movement action in an active game session during the agent's turn
Attacks that exploit this kind of access
Mover en la grilla 20x14. Solo en tu turno. 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 move: 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.
move 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 move 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 move. 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.
move 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 →