AI agents call lucille_round_strategy to retrieve information from Lucille without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns advisory data about game state without altering any data, executing external operations, or moving funds. It is purely informational, making it a Read operation with low severity since misuse would only provide suboptimal game suggestions, not compromise systems or assets.
From the tool's definition Tool description states it 'Get[s] strategic advice' — a retrieval operation that provides information about the current round (threshold, phase, personality tips, cost, and how to play).
Attacks that exploit this kind of access
Get strategic advice for the current round — threshold, phase, personality tips, cost, and how to play. It is categorised as a Read tool in the Lucille MCP Server, which means it retrieves data without modifying state.
Register the Lucille MCP server in PolicyLayer and add a rule for lucille_round_strategy: 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 Lucille. Nothing to install.
lucille_round_strategy 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 lucille_round_strategy 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 lucille_round_strategy. 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.
lucille_round_strategy is provided by the Lucille MCP server (lucille-mcp-server). 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 →