Remove um cargo pelo ID.
AI agents call rhid_remover_cargo to permanently remove resources in RHID MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly deletes a job position/role record from the RHiD system. This is a destructive operation that cannot be undone and affects organizational structure and employee records. While not directly financial, the deletion of a cargo (position) could have cascading effects on employee management, payroll, and reporting systems.
From the tool's definition Tool name 'rhid_remover_cargo' and description 'Remove um cargo pelo ID' (Remove a position/role by ID) explicitly perform deletion of organizational data.
Attacks that exploit this kind of access
Remove um cargo pelo ID. It is categorised as a Destructive tool in the RHID MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the RHID MCP Server MCP server in PolicyLayer and add a rule for rhid_remover_cargo: 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 RHID MCP Server. Nothing to install.
rhid_remover_cargo is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the rhid_remover_cargo 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 rhid_remover_cargo. 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.
rhid_remover_cargo is provided by the RHID MCP Server MCP server (miranda-ale/rhdi-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 →