AI agents call get_combat_log 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 tool queries existing game state information (combat history, battle records) without modifying, deleting, or executing any operations. It falls squarely into the Read category—information retrieval for strategic analysis. The low severity reflects that accessing game intelligence data poses minimal risk; misuse would only affect decision-making, not the game state itself.
From the tool's definition Tool description states it retrieves 'recent combat history showing battles, units involved, damage dealt, and active conflicts.' The verb 'Get' and action of retrieving historical game data indicates read-only access with no side effects.
Attacks that exploit this kind of access
Get recent combat history showing battles, units involved, damage dealt, and active conflicts. 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 get_combat_log: 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.
get_combat_log 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_combat_log 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_combat_log. 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_combat_log 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 →