AI agents call precedents_list to retrieve information from Legalize without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves legal precedent data via GitHub REST API without modifying, deleting, or executing any operations. It is a read-only retrieval function that has no side effects on the underlying data or external systems. Low severity due to minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'precedents_list' and description '판례 목록을 조회합니다' (queries/retrieves a list of precedents) indicate a retrieval operation. No modification, deletion, or execution keywords present.
Documented attack patterns abuse exactly the kind of access precedents_list gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Legalize, and nothing reaches the server without passing your rules. This is the rule we recommend for precedents_list:
{
"version": "1",
"default": "deny",
"tools": {
"precedents_list": {}
}
}precedents_list 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.
판례 목록을 조회합니다. It is categorised as a Read tool in the Legalize MCP Server, which means it retrieves data without modifying state.
Register the Legalize MCP server in PolicyLayer and add a rule for precedents_list: 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 Legalize. Nothing to install.
precedents_list 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 precedents_list 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 precedents_list. 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.
precedents_list is provided by the Legalize MCP server (legalize-kr/cli-tools). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Legalize, 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.
10 Legalize tools catalogued and risk-classified — across an index of 43,000+ MCP servers.