AI agents call get_friend_list to retrieve information from Mcp Steam without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves friend list data from Steam, which is a read-only query operation. No data is created, modified, deleted, or executed. The action has no side effects beyond fetching existing information. Severity is low because friend list information is generally non-sensitive metadata that would not cause significant harm if exposed to an AI agent.
From the tool's definition Tool name is 'get_friend_list' and description states 'Get a Steam friends list' — uses 'Get' verb indicating retrieval without modification or side effects.
Attacks that exploit this kind of access
Get a Steam friends list. It is categorised as a Read tool in the Mcp Steam MCP Server, which means it retrieves data without modifying state.
Register the Mcp Steam MCP server in PolicyLayer and add a rule for get_friend_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 Mcp Steam. Nothing to install.
get_friend_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_friend_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_friend_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_friend_list is provided by the Mcp Steam MCP server (obrien-matthew/mcp-steam). 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 →