AI agents call read_existing_rules to retrieve information from Trae Rules Generator MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries rule file data without any side effects or state changes. It is a pure read operation that fits the Read category definition (retrieves or queries data; no side effects). The low severity reflects minimal risk—an AI agent misusing this would only gain visibility into existing rule configurations, with no destructive or operational consequences.
From the tool's definition Tool name: 'read_existing_rules'; description indicates it reads/retrieves rule file content ('读取现有的规则文件内容' = 'reads existing rule file content'). No modification, deletion, or execution capability described.
Documented attack patterns abuse exactly the kind of access read_existing_rules gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trae Rules Generator MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for read_existing_rules:
{
"version": "1",
"default": "deny",
"tools": {
"read_existing_rules": {}
}
}read_existing_rules is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
读取现有的规则文件内容. It is categorised as a Read tool in the Trae Rules Generator MCP MCP Server, which means it retrieves data without modifying state.
Register the Trae Rules Generator MCP server in PolicyLayer and add a rule for read_existing_rules: 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 Trae Rules Generator MCP. Nothing to install.
read_existing_rules 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 read_existing_rules 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 read_existing_rules. 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.
read_existing_rules is provided by the Trae Rules Generator MCP server (xiaochenwin/trae-rules-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Trae Rules Generator MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Trae Rules Generator MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.