AI agents call get_axie_equipment to retrieve information from Axie without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries game data (equipment state) without side effects. It follows the Read pattern: retrieves or queries data; no side effects. Similar sibling tools (get_axie, get_land, get_leaderboard, get_market_stats) all query game information. Misuse would have minimal blast radius—an agent could only retrieve equipment details it has access to, with no ability to modify, destroy, or move assets.
From the tool's definition Tool name is 'get_axie_equipment' and description states it retrieves equipment and accessories 'currently equipped on' Axies. The verb 'get' and retrieval-only pattern matches the Read category.
Attacks that exploit this kind of access
Get the equipment and accessories currently equipped on one or more Axies. It is categorised as a Read tool in the Axie MCP Server, which means it retrieves data without modifying state.
Register the Axie MCP server in PolicyLayer and add a rule for get_axie_equipment: 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 Axie. Nothing to install.
get_axie_equipment 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_axie_equipment 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_axie_equipment. 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_axie_equipment is provided by the Axie MCP server (jackdlogan/axie-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 →