AI agents call list_saves to retrieve information from Civ6mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation that queries the file system for save file metadata. It has no side effects, does not execute code, does not modify or delete data, and does not involve financial operations. The blast radius of misuse is minimal — an AI agent could only discover which save files exist, which is harmless information disclosure about the local game state.
From the tool's definition Tool is named 'list_saves' and description states 'List all Civilization VI save files' — it retrieves and enumerates existing save files without modification, deletion, or execution of code.
Attacks that exploit this kind of access
List all Civilization VI save files. Saves are located at: ${getSavesDirectory()}. It is categorised as a Read tool in the Civ6mcp MCP Server, which means it retrieves data without modifying state.
Register the Civ6 MCP server in PolicyLayer and add a rule for list_saves: 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 Civ6mcp. Nothing to install.
list_saves 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_saves 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_saves. 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_saves is provided by the Civ6 MCP server (lowrykun/civ6mcp). 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 →