AI agents call search_design_rules to retrieve information from MCP Modus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves design rule documentation based on search criteria. It performs a read-only lookup operation against a knowledge base of design guidelines, with no side effects, data modifications, or code execution. The blast radius of misuse is minimal—an AI agent could only retrieve information it shouldn't access, not modify systems or execute operations.
From the tool's definition Tool name 'search_design_rules' and description 'Search across all design rules by keyword or term' indicate a query/search operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Search across all design rules by keyword or term. It is categorised as a Read tool in the MCP Modus MCP Server, which means it retrieves data without modifying state.
Register the MCP Modus MCP server in PolicyLayer and add a rule for search_design_rules: 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 MCP Modus. Nothing to install.
search_design_rules 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_design_rules 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_design_rules. 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_design_rules is provided by the MCP Modus MCP server (julianoczkowski/mcp-modus). 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 →