AI agents call lookup_bgbl 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 lookup_bgbl tool retrieves information about Bundesgesetzblatt (Federal Law Gazette) entries. It returns data (title and amended laws) without creating, modifying, deleting, or executing any operations. This is a standard read/query operation against a public legal database API with no side effects or state changes possible.
From the tool's definition Tool description states 'Look up...and return' - a retrieval operation with no modification capability. The RIS-MCP server is explicitly designed for 'full-text search, paragraph retrieval, historical versions, statute lookup' - all read-only operations…
Attacks that exploit this kind of access
Look up an authentic Bundesgesetzblatt entry and return its title and amended laws. 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 lookup_bgbl: 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.
lookup_bgbl 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 lookup_bgbl 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 lookup_bgbl. 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.
lookup_bgbl 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 →