AI agents call block_explode to permanently remove resources in AutoCAD MCP Pro — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
In AutoCAD, 'explode' is a well-known destructive operation that irreversibly decomposes a block reference (or other compound entity) into its constituent primitives, destroying the original block instance and losing block-level attributes and associations. This operation cannot be undone in an automated/headless context. The name strongly implies this standard CAD behavior.
From the tool's definition Tool name 'block_explode' on an AutoCAD automation server; description is empty.
Documented attack patterns abuse exactly the kind of access block_explode gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AutoCAD MCP Pro, and nothing reaches the server without passing your rules. This is the rule we recommend for block_explode:
{
"version": "1",
"default": "deny",
"hide": [
"block_explode"
]
} block_explode disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
block_explode. It is categorised as a Destructive tool in the AutoCAD MCP Pro MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AutoCAD MCP Pro MCP server in PolicyLayer and add a rule for block_explode: 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 AutoCAD MCP Pro. Nothing to install.
block_explode 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 block_explode 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 block_explode. 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.
block_explode is provided by the AutoCAD MCP Pro MCP server (u-c4n/autocad-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AutoCAD MCP Pro, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
108 AutoCAD MCP Pro tools catalogued and risk-classified — across an index of 43,000+ MCP servers.