AI agents call get_paragraph 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 specific legal text content from a public database without any side effects. It cannot modify, delete, or execute anything—it simply fetches and returns data. This is a classic Read operation with minimal risk; the worst case is retrieving irrelevant or sensitive legal information, but the operation itself is non-destructive and reversible (a subsequent read returns the same data).
From the tool's definition Tool description states 'Fetch one paragraph or a range of paragraphs from an Austrian statute' - a retrieval operation with no modification or execution capability.
Attacks that exploit this kind of access
Fetch one paragraph or a range of paragraphs from an Austrian statute. 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 get_paragraph: 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.
get_paragraph 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_paragraph 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_paragraph. 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_paragraph 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 →