Delete a TDX configuration item
AI agents call tdx-cmdb-delete to permanently remove resources in TDX MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data from the CMDB, a critical system-of-record for IT infrastructure. Deletion of configuration items can break downstream dependencies, impact change tracking, and require manual recovery. Even if soft-delete is implemented, the primary function is destructive.
From the tool's definition Tool name includes 'delete' and description states 'Delete a TDX configuration item' — a configuration item in a CMDB (Configuration Management Database) is core infrastructure data that, once deleted, cannot be automatically recovered without backup…
Attacks that exploit this kind of access
Delete a TDX configuration item. It is categorised as a Destructive tool in the TDX MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TDX MCP Server MCP server in PolicyLayer and add a rule for tdx-cmdb-delete: 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 TDX MCP Server. Nothing to install.
tdx-cmdb-delete 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 tdx-cmdb-delete 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 tdx-cmdb-delete. 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.
tdx-cmdb-delete is provided by the TDX MCP Server MCP server (umzcio/teamdynamix-mcp-connector). 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 →