search_clauses
AI agents call search_clauses to retrieve information from Cuad Audit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the name and server context (contract auditing), this tool retrieves or queries contract clause data with no indication of side effects. The empty description reduces confidence slightly, but the naming convention and read-only pattern in similar audit tools (get_standard) strongly suggest this is a retrieval operation. No destructive, financial, or code execution capability is evident.
From the tool's definition Tool name 'search_clauses' indicates query/retrieval of contract clauses; empty description prevents identification of data modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
search_clauses. It is categorised as a Read tool in the Cuad Audit MCP Server, which means it retrieves data without modifying state.
Register the Cuad Audit MCP server in PolicyLayer and add a rule for search_clauses: 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 Cuad Audit. Nothing to install.
search_clauses 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_clauses 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_clauses. 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_clauses is provided by the Cuad Audit MCP server (master997/luminance). 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 →