AI agents use set_custom_field to create or update resources in Lawruler — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lawruler environment.
This tool creates or modifies lead data reversibly within a legal CRM system. It does not delete data (ruling out Destructive), does not execute arbitrary code (ruling out Execute), and does not involve financial transactions (ruling out Financial).
From the tool's definition Tool name 'set_custom_field' and description 'Set a custom field on a lead' indicates modification of lead data. The tool updates custom fields (identified by API parameter names like 'custom2413') without deleting or destroying data.
Attacks that exploit this kind of access
Set a custom field on a lead. field_name is the API parameter name (e.g., custom2413). It is categorised as a Write tool in the Lawruler MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lawruler MCP server in PolicyLayer and add a rule for set_custom_field: 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 Lawruler. Nothing to install.
set_custom_field is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_custom_field 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 set_custom_field. 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.
set_custom_field is provided by the Lawruler MCP server (rosenadvertising/lawruler-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 →