AI agents call get_game_schema 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 queries and returns informational data about game achievements and statistics. It has no side effects, cannot modify data, execute code, delete resources, or affect financial systems. The action verb 'get' combined with the read-only nature of retrieving schema information clearly places this in the Read category with low risk.
From the tool's definition Tool name 'get_game_schema' and description states it retrieves 'the full list of stats and achievements for a game, including display names, descriptions, and icons' — purely a data retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Get the full list of stats and achievements for a game, including display names, descriptions, and icons. 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_game_schema: 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_game_schema 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_game_schema 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_game_schema. 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_game_schema 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 →