Get game recommendations based on what a friend owns but you don't.
AI agents call get_friend_game_recommendations to retrieve information from PersonalizationMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation as it retrieves and queries data (friend's game ownership and recommendations) with no side effects or data modification. Severity is medium rather than low because it accesses personal data about a friend's gaming habits and library, which could enable social engineering or privacy violations if misused by an AI agent; however, it does not modify, delete, or move money.
From the tool's definition Tool name 'get_friend_game_recommendations' and description 'Get game recommendations based on what a friend owns but you don't' indicate retrieval of data without modification. The tool reads friend's game library and compares it to generate recommendations.
Documented attack patterns abuse exactly the kind of access get_friend_game_recommendations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PersonalizationMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_friend_game_recommendations:
{
"version": "1",
"default": "deny",
"tools": {
"get_friend_game_recommendations": {}
}
}get_friend_game_recommendations is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get game recommendations based on what a friend owns but you don't. It is categorised as a Read tool in the PersonalizationMCP MCP Server, which means it retrieves data without modifying state.
Register the Personalization MCP server in PolicyLayer and add a rule for get_friend_game_recommendations: 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 PersonalizationMCP. Nothing to install.
get_friend_game_recommendations 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_friend_game_recommendations 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_friend_game_recommendations. 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_friend_game_recommendations is provided by the Personalization MCP server (yangliangwei/personalizationmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 88 PersonalizationMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
88 PersonalizationMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.