AI agents call lucille_history 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.
lucille_history retrieves and displays past game history and statistics. There is no indication it modifies, deletes, or executes any operations. The tool simply queries and presents historical information, making it a straightforward Read operation with minimal risk if misused by an agent.
From the tool's definition Tool description states 'See game attempts — recent feed, filter by round (personality), or by player. Shows scores, messages, and Lucille'.
Attacks that exploit this kind of access
See game attempts — recent feed, filter by round (personality), or by player. Shows scores, messages, and Lucille. 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_history: 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_history 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_history 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_history. 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_history 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 →