AI agents call steam_help 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 and displays help information and authentication guidance. It does not query live data, modify anything, execute code, delete content, or handle financial transactions. It is purely informational/read-only, making it the lowest risk category with minimal blast radius if misused.
From the tool's definition Tool name 'steam_help' and description stating it provides 'Multi-level help for Steam-MCP portmanteau tools and auth requirements' indicates a help/documentation retrieval function with no side effects.
Attacks that exploit this kind of access
Multi-level help for Steam-MCP portmanteau tools and auth requirements. 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_help: 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_help 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_help 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_help. 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_help 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 →