AI agents call search_law to retrieve information from Ris without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries legal data from the Austrian federal law database without modifying it. The empty description prevents higher confidence, but the server's stated purpose (search, retrieval, lookup) and sibling tools (all get_* and lookup_* functions) indicate read-only operations. No data is created, modified, deleted, or irreversibly changed.
From the tool's definition Tool name 'search_law' combined with server description's stated capabilities of 'full-text search' and 'paragraph retrieval' via a read-only public API (RIS OGD). The server exposes existing legal data with no mutation capabilities mentioned.
Attacks that exploit this kind of access
search_law. It is categorised as a Read tool in the Ris MCP Server, which means it retrieves data without modifying state.
Register the Ris MCP server in PolicyLayer and add a rule for search_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 Ris. Nothing to install.
search_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_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_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_law is provided by the Ris MCP server (noahpfi/ris-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 →