AI agents call list_updates to retrieve information from Law Diff without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a database or service to retrieve metadata about law updates on a specific date. It performs no writes, deletions, code execution, or financial transactions. It is a straightforward read operation that retrieves historical information about Japanese e-Gov law amendments. The low severity reflects minimal blast radius if misused — an agent could only retrieve publicly available legal information.
From the tool's definition Tool description states it 'List laws updated' and 'Returns amendment metadata and law revision IDs' — purely retrieving and querying data without modification.
Attacks that exploit this kind of access
List laws updated in e-Gov Law Search on a specific date. Returns amendment metadata and law revision IDs when available. It is categorised as a Read tool in the Law Diff MCP Server, which means it retrieves data without modifying state.
Register the Law Diff MCP server in PolicyLayer and add a rule for list_updates: 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 Law Diff. Nothing to install.
list_updates 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 list_updates 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 list_updates. 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.
list_updates is provided by the Law Diff MCP server (shayouworld/law-diff-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 →