clash_grade_war
AI agents call clash_grade_war to retrieve information from Clash of Clans MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty tool description, the naming pattern, server purpose (clan analysis via API reads), and sibling tool inventory strongly indicate this tool retrieves or analyzes war data without side effects. Grading is a computational/analytical operation on read data, not a write, execute, or destructive action.
From the tool's definition Tool name 'clash_grade_war' and sibling tools (clash_api_get, clash_get_clan, clash_get_clan_members, clash_get_current_war, clash_get_player, clash_get_warlog) are all retrieval/analysis operations.
Attacks that exploit this kind of access
clash_grade_war. It is categorised as a Read tool in the Clash of Clans MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Clash of Clans MCP Server MCP server in PolicyLayer and add a rule for clash_grade_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 Clash of Clans MCP Server. Nothing to install.
clash_grade_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 clash_grade_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 clash_grade_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.
clash_grade_war is provided by the Clash of Clans MCP Server MCP server (justinritchie/clash-of-clans-mcp). 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 →