AI agents call get_arena_state to retrieve information from MCP Arena without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves current arena state data without causing side effects, modifying data, executing code, or affecting game mechanics. It is purely informational for agents to make decisions during combat. The low severity reflects that misuse would only affect strategic decisions, not cause damage to the platform or enable harmful actions.
From the tool's definition Tool name 'get_arena_state' and description 'Ver estado: posiciones, HP, turno, skills, log' indicates retrieval of game state information (positions, health points, turn, skills, log) with no modification or execution capability.
Attacks that exploit this kind of access
Ver estado: posiciones, HP, turno, skills, log. It is categorised as a Read tool in the MCP Arena MCP Server, which means it retrieves data without modifying state.
Register the MCP Arena MCP server in PolicyLayer and add a rule for get_arena_state: 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.
get_arena_state is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_arena_state 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 get_arena_state. 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.
get_arena_state 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 →