AI agents call search_library 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 only retrieves and filters data from the user's Steam library without modifying, deleting, or executing any external actions. It is a read-only operation that searches existing data. Low severity because misuse would only return unwanted query results, with no side effects or blast radius.
From the tool's definition The tool description states it "Search[es] and filter[s] your Steam library" — purely query operations. The server description confirms this server "Query[s] your games, playtime, recently played history" with "Zero-config install via npx steam-mcp." The tool…
Attacks that exploit this kind of access
Search and filter your Steam library by name, playtime range, or unplayed status. 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 search_library: 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.
search_library 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 search_library 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 search_library. 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.
search_library is provided by the Steam MCP server (jkiley129/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 →