AI agents call get_revision_text 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 and fetches Japanese e-Gov law information without creating, modifying, deleting, or executing any operations. It is a pure data retrieval operation with no side effects. The sibling tools (diff_revisions, find_revisions, list_updates) reinforce that this server family performs read-only legal history and comparison operations.
From the tool's definition Tool 'retrieves' law text and 'returns metadata, source URLs, and a plain-text preview' with no modification capability described. The description explicitly uses read-only language: 'retrieve', 'returns'.
Attacks that exploit this kind of access
Retrieve law text for a current law ID or e-Gov law revision ID. Returns metadata, source URLs, and a plain-text preview. 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 get_revision_text: 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.
get_revision_text 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 get_revision_text 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 get_revision_text. 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.
get_revision_text 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 →