AI agents call ping to retrieve information from Cocos MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a connectivity/health-check tool that only queries the editor's status. It has no side effects, makes no modifications, and simply returns whether the editor is reachable. Lowest possible blast radius.
From the tool's definition Check if the Cocos Creator editor is connected and responsive.
Attacks that exploit this kind of access
Check if the Cocos Creator editor is connected and responsive. It is categorised as a Read tool in the Cocos MCP MCP Server, which means it retrieves data without modifying state.
Register the Cocos MCP server in PolicyLayer and add a rule for ping: 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 Cocos MCP. Nothing to install.
ping 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 ping 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 ping. 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.
ping is provided by the Cocos MCP server (wanghehacker/cocos-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 →