AI agents call list_games to retrieve information from Zmachine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query to enumerate available game files. It has no side effects, cannot modify data, execute code, or trigger any external operations. The blast radius of misuse is minimal—an agent could only discover what games are available, which is not sensitive information in a gaming context.
From the tool's definition Tool lists available Z-Machine story files with no modification or execution capability. The description states 'List all Z-Machine story files' which is a pure retrieval operation.
Attacks that exploit this kind of access
List all Z-Machine story files available to play. It is categorised as a Read tool in the Zmachine MCP Server, which means it retrieves data without modifying state.
Register the Zmachine MCP server in PolicyLayer and add a rule for list_games: 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 Zmachine. Nothing to install.
list_games 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 list_games 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 list_games. 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.
list_games is provided by the Zmachine MCP server (jonathan-meyer/zmachine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
list_games is one line of Zmachine's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →