compare_old_new
AI agents call compare_old_new 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.
The tool name 'compare_old_new' strongly implies comparing old and new versions of legal text (e.g., legislative amendments), which is a read/retrieval operation. The server context focuses on searching and retrieving legal information with no write or execute capabilities evident. However, the empty description lowers confidence significantly.
From the tool's definition Tool name 'compare_old_new' and empty description; contextually on a Korean Law MCP server with sibling tools like 'get_article_history' and 'search_korean_law' suggesting read-only legal document comparison
Attacks that exploit this kind of access
compare_old_new. 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 compare_old_new: 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.
compare_old_new 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 compare_old_new 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 compare_old_new. 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.
compare_old_new 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 →