AI agents call get_statute 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.
The tool performs a read-only retrieval operation on legal statute data. There is no modification, deletion, execution of external code, or financial transaction. The data source is a public federal law database, and the operation simply fetches pre-existing content. The blast radius of misuse is minimal—an agent could retrieve unwanted legal texts, but no data is altered, destroyed, or financial harm caused.
From the tool's definition Tool 'get_statute' is described as fetching (retrieving) 'the preamble and first page of paragraphs for a statute.' The verb 'fetch' indicates data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Fetch the preamble and first page of paragraphs for a 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_statute: 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_statute 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_statute 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_statute. 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_statute 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 →