AI agents call get_paragraph_at 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 and queries historical legislative text data without side effects. It performs a read operation on the RIS OGD API to obtain past versions of legal paragraphs, which is consistent with the 'Read' category. The operation is informational and creates no change to the underlying data.
From the tool's definition Tool description states 'Fetch the historical version of a paragraph as it read on a given date' — retrieval-only operation with no modification, creation, or deletion capabilities.
Attacks that exploit this kind of access
Fetch the historical version of a paragraph as it read on a given date. 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_at: 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_at 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_at 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_at. 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_at 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 →