Get global aggregated stats for a game (requires knowing stat names from schema)
AI agents call get_global_game_stats to retrieve information from Steam MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves statistical data about games in aggregate form. It has no capability to modify, delete, or execute operations—it purely fetches information from the Steam Web API. The requirement to know stat names beforehand further confirms this is a passive lookup. No financial, destructive, or execution side effects are possible.
From the tool's definition Tool retrieves global aggregated stats for a game; described as a GET operation that 'get's data with no modification capability.
Attacks that exploit this kind of access
Get global aggregated stats for a game (requires knowing stat names from schema). It is categorised as a Read tool in the Steam MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Steam MCP Server MCP server in PolicyLayer and add a rule for get_global_game_stats: 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 MCP Server. Nothing to install.
get_global_game_stats 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_global_game_stats 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_global_game_stats. 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_global_game_stats is provided by the Steam MCP Server MCP server (sharkusmanch/steam-mcp-server). 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 →