AI agents call get_friends_list 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 a player's friend list from Steam Web API with no side effects—no data is created, modified, deleted, or money moved. It is a straightforward read operation. Severity is low because exposing friend lists carries minimal blast radius; this is already public or semi-public information on Steam profiles.
From the tool's definition Tool name 'get_friends_list' and server description explicitly listing 'friend lists' as a queryable data type. The sibling tools (get_badges, get_owned_games, get_player_achievements, etc.) are all retrieval operations.
Attacks that exploit this kind of access
Get a player. 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_friends_list: 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_friends_list 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_friends_list 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_friends_list. 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_friends_list 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 →