Full-text search across agency guidance documents (circulars, opinions, rulings).
AI agents call search_agency_guidance to retrieve information from German Law MCP Server 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 existing agency guidance without creating, modifying, deleting, or executing operations. It has minimal blast radius if misused by an AI agent—worst case being retrieval of sensitive legal guidance, but without the ability to alter documents or trigger external actions. This is a standard Read category tool.
From the tool's definition Tool description explicitly states 'Full-text search across agency guidance documents' which is a retrieval operation.
Attacks that exploit this kind of access
Full-text search across agency guidance documents (circulars, opinions, rulings). It is categorised as a Read tool in the German Law MCP Server MCP Server, which means it retrieves data without modifying state.
Register the German Law MCP Server MCP server in PolicyLayer and add a rule for search_agency_guidance: 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 German Law MCP Server. Nothing to install.
search_agency_guidance 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_agency_guidance 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_agency_guidance. 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_agency_guidance is provided by the German Law MCP Server MCP server (nenna-ai-gmbh/german-law-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 →