AI agents call get_user_groups to retrieve information from Steam without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing group membership information from a Steam profile. It is a read-only query operation that returns data without creating, modifying, deleting, or executing any actions. The minimal risk is due to the purely informational nature of the data returned and the fact that it requires the profile to be publicly visible.
From the tool's definition Tool name 'get_user_groups' and description 'Get a list of Steam group IDs' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get a list of Steam group IDs a player belongs to. Requires public profile. It is categorised as a Read tool in the Steam MCP Server, which means it retrieves data without modifying state.
Register the Steam MCP server in PolicyLayer and add a rule for get_user_groups: 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 Steam. Nothing to install.
get_user_groups 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_user_groups 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_user_groups. 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_user_groups is provided by the Steam MCP server (matheusslg/steam-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 →