get-current-war
AI agents call get-current-war to retrieve information from Mc Server Clash Of Clans without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves current war information from the Clash of Clans API. It queries data without side effects, matching the Read category. Severity is low as it only exposes public gaming data. Confidence is high despite empty description because context from server purpose and sibling tool patterns clearly indicates data retrieval.
From the tool's definition Tool name 'get-current-war' and sibling tools like 'get-player', 'get-clan', 'get-war-log' are all retrieval operations. Server description states it 'can get player, clan information, analyze ongoing wars, as well as war logs'.
Attacks that exploit this kind of access
get-current-war. It is categorised as a Read tool in the Mc Server Clash Of Clans MCP Server, which means it retrieves data without modifying state.
Register the Mc Server Clash Of Clans MCP server in PolicyLayer and add a rule for get-current-war: 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 Mc Server Clash Of Clans. Nothing to install.
get-current-war 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-current-war 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-current-war. 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-current-war is provided by the Mc Server Clash Of Clans MCP server (saunved/mcp-server-clash-of-clans). 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 →