This record as markdown: /tools/atharva-joshi77-cdp-mcp/cdp-delete-role.md
What cdp_delete_role does on CDP MCP Server
AI agents call cdp_delete_role to permanently remove resources in CDP MCP Server, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why cdp_delete_role is rated Critical
This tool permanently removes a role from the CDP system by ID, which cannot be undone. Deletion is an irreversible action that cannot be recovered or rolled back. While the blast radius is limited to role management (not data destruction across the entire platform), deletion operations are classified as Destructive per the taxonomy rules.
From the tool's definition Tool name is 'cdp_delete_role' with description 'Delete a role by ID'. The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
The rule that runs cdp_delete_role safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CDP MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cdp_delete_role, this is the rule to start with:
cdp_delete_role is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect CDP MCP Server, apply this rule, and every cdp_delete_role call is checked against it from then on.
Questions about cdp_delete_role
Delete a role by ID. It is categorised as a Destructive tool in the CDP MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CDP MCP Server MCP server in PolicyLayer and add a rule for cdp_delete_role: 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 CDP MCP Server. Nothing to install.
cdp_delete_role 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 cdp_delete_role 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 cdp_delete_role. 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.
cdp_delete_role is provided by the CDP MCP Server MCP server (atharva-joshi77/cdp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CDP MCP Server, and thousands of servers like it.
Across the catalogue