audit_clause
AI agents call audit_clause 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.
The tool performs audit analysis—comparing contract clauses against standards and retrieving/evaluating evidence. This is fundamentally a read operation: it queries, analyzes, and reports on existing contract data without creating, modifying, deleting, or executing code.
From the tool's definition Tool 'audit_clause' operates within an audit server that 'audits a contract liability clause against a derived company standard, producing a verdict only when grounded in retrieved evidence.' The sibling tool 'search_clauses' and 'get_standard' indicate data…
Attacks that exploit this kind of access
audit_clause. 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 audit_clause: 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.
audit_clause 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 audit_clause 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 audit_clause. 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.
audit_clause 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 →