[Google Play] Search for apps
AI agents call gp_search to retrieve information from Store Scraper MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves app information from Google Play Store, which is a read-only operation with no side effects. The blast radius of misuse is minimal—an AI agent searching for apps cannot cause harm beyond potentially excessive API consumption or information gathering. Classification as Read is appropriate.
From the tool's definition Tool name 'gp_search' and description 'Search for apps' indicate a query operation that retrieves data from Google Play Store without modifying, deleting, or executing code.
Attacks that exploit this kind of access
[Google Play] Search for apps. It is categorised as a Read tool in the Store Scraper MCP MCP Server, which means it retrieves data without modifying state.
Register the Store Scraper MCP server in PolicyLayer and add a rule for gp_search: 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 Store Scraper MCP. Nothing to install.
gp_search 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 gp_search 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 gp_search. 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.
gp_search is provided by the Store Scraper MCP server (miguelalvred/mobile-store-scraper-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 →