AI agents call search_items to retrieve information from Playfab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a query operation against a catalog to retrieve matching items. It has no capability to create, modify, delete, or execute operations—only to read and return information. The low severity reflects that misuse would result in information disclosure rather than damage to game state or financial impact.
From the tool's definition Tool description states 'Searches for items in the PlayFab catalog' and explicitly says 'Use this when you need to find items by name, type, or other properties.' The verb 'search' and 'find' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Searches for items in the PlayFab catalog (Economy v2). Use this when you need to find items by name, type, or other properties. It is categorised as a Read tool in the Playfab MCP Server, which means it retrieves data without modifying state.
Register the Playfab MCP server in PolicyLayer and add a rule for search_items: 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 Playfab. Nothing to install.
search_items 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 search_items 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 search_items. 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.
search_items is provided by the Playfab MCP server (@akiojin/playfab-mcp-server). 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 →