AI agents call bs_get_state to retrieve information from Ttt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves game state information (attack grids and fleet status) without modifying, executing external operations, or causing irreversible changes. It is a pure query operation with no side effects, fitting squarely in the Read category. The low severity reflects the limited blast radius—an AI agent retrieving game state poses minimal risk in a game context.
From the tool's definition Description states 'Get the current battle map' and explicitly 'does not count as a shot', indicating retrieval of state without side effects. Named 'get_state' which follows read-operation conventions.
Attacks that exploit this kind of access
Get the current battle map — both attack grids and fleet status. Free, does not count as a shot. It is categorised as a Read tool in the Ttt MCP Server, which means it retrieves data without modifying state.
Register the Ttt MCP server in PolicyLayer and add a rule for bs_get_state: 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 Ttt. Nothing to install.
bs_get_state 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 bs_get_state 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 bs_get_state. 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.
bs_get_state is provided by the Ttt MCP server (srmtech-git/mcparcade). 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 →