AI agents call get_session_info 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 retrieves information about an active game session. It performs a query operation to obtain session state and status without creating, modifying, deleting, or executing any operations. The action is read-only and has no irreversible consequences. Even in a misuse scenario, an AI agent could only learn about existing game state, not alter it or trigger external effects.
From the tool's definition Tool name 'get_session_info' and description 'Get the current status and state of an active game session' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get the current status and state of an active game session. 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 get_session_info: 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.
get_session_info 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_session_info 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_session_info. 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_session_info 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.
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 →