AI agents call preview_assignment_rule to retrieve information from ComplyOS without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The word 'preview' strongly implies a non-destructive, read-only action that shows what an assignment rule would do without applying it. In the context of a compliance auditing engine for LMS, previewing an assignment rule likely retrieves and displays rule logic or its projected effects. However, the empty description reduces confidence.
From the tool's definition Tool name 'preview_assignment_rule' suggests a read/preview operation; description is empty and uninformative.
Attacks that exploit this kind of access
preview_assignment_rule. It is categorised as a Read tool in the ComplyOS MCP Server, which means it retrieves data without modifying state.
Register the ComplyOS MCP server in PolicyLayer and add a rule for preview_assignment_rule: 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 ComplyOS. Nothing to install.
preview_assignment_rule 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 preview_assignment_rule 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 preview_assignment_rule. 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.
preview_assignment_rule is provided by the ComplyOS MCP server (simongonzalezdc/complyos). 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 →