AI agents call get_game_reviews 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 retrieves public Steam game reviews without any side effects. It does not create, modify, delete, or execute any actions. The data returned is read-only information. Classification as Read is appropriate with low severity since unauthorized access to public review data poses minimal risk.
From the tool's definition Tool retrieves reviews for a Steam game, including sentiment summary and review text. Descriptive verbs indicate data retrieval: 'Get reviews' and operations are passive queries with no modification or deletion of data.
Attacks that exploit this kind of access
Get reviews for a Steam game with sentiment summary (score, positive/negative counts) and individual review text. 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_reviews: 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_reviews 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_reviews 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_reviews. 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_reviews 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 →