search_korean_law
AI agents call search_korean_law to retrieve information from Korean Law MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval from a legal database. The server explicitly describes search and retrieval functionality. No modification, execution, deletion, or financial operations are indicated. Searching legal resources is a read-only operation with no capability to alter data or trigger external effects.
From the tool's definition Tool name 'search_korean_law' combined with server's stated capability to 'search and retrieve South Korean statutes, precedents, and administrative rules.' Sibling tools include 'search_law_articles', 'search_legal_terms', and…
Attacks that exploit this kind of access
search_korean_law. It is categorised as a Read tool in the Korean Law MCP MCP Server, which means it retrieves data without modifying state.
Register the Korean Law MCP server in PolicyLayer and add a rule for search_korean_law: 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 Korean Law MCP. Nothing to install.
search_korean_law 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 search_korean_law 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 search_korean_law. 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.
search_korean_law is provided by the Korean Law MCP server (seo-jinseok/korean-law-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 →