AI agents call check_app_store_info to retrieve information from Mcp Apple without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing public data about applications available in the Apple App Store. No data is created, modified, deleted, or financial transactions are involved. The operation has no side effects beyond returning information to the user.
From the tool's definition Tool queries app information from the Apple App Store with no indication of side effects. Verbs 'look up' and 'search' indicate retrieval-only operations.
Attacks that exploit this kind of access
Look up app information from the Apple App Store. It is categorised as a Read tool in the Mcp Apple MCP Server, which means it retrieves data without modifying state.
Register the Mcp Apple MCP server in PolicyLayer and add a rule for check_app_store_info: 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 Apple. Nothing to install.
check_app_store_info 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 check_app_store_info 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 check_app_store_info. 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.
check_app_store_info is provided by the Mcp Apple MCP server (markswendsen-code/mcp-apple). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
check_app_store_info is one line of Mcp Apple's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →