AI agents call steam_system to retrieve information from Steam-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves system status and configuration information about Steam-MCP and SteamCMD without modifying, executing commands, deleting data, or moving money. It is a diagnostic/monitoring tool that falls squarely into the Read category. The low severity reflects minimal blast radius if misused—an agent could only access existing status information.
From the tool's definition Tool name 'steam_system' combined with description indicating it performs 'status' checks and 'configuration check' of Steam systems. These are informational queries with no side effects.
Attacks that exploit this kind of access
Steam-MCP system status and SteamCMD configuration check. It is categorised as a Read tool in the Steam-MCP MCP Server, which means it retrieves data without modifying state.
Register the Steam- MCP server in PolicyLayer and add a rule for steam_system: 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. Nothing to install.
steam_system 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 steam_system 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 steam_system. 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.
steam_system is provided by the Steam- MCP server (sandraschi/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 →