AI agents call remove_plan_run to permanently remove resources in MCPacer — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes a workout entry from a training plan, which cannot be easily undone without manual re-entry. While the blast radius is limited to training plans (not production systems or financial data), the destructive nature of permanent deletion without recovery options places it in the Destructive category rather than Write.
From the tool's definition The tool 'remove_plan_run' with description 'Remove a workout from a week' performs an irreversible deletion operation on training plan data.
Documented attack patterns abuse exactly the kind of access remove_plan_run gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCPacer, and nothing reaches the server without passing your rules. This is the rule we recommend for remove_plan_run:
{
"version": "1",
"default": "deny",
"hide": [
"remove_plan_run"
]
}remove_plan_run 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.
Remove a workout from a week. It is categorised as a Destructive tool in the MCPacer MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCPacer MCP server in PolicyLayer and add a rule for remove_plan_run: 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 MCPacer. Nothing to install.
remove_plan_run 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 remove_plan_run 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 remove_plan_run. 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.
remove_plan_run is provided by the MCPacer MCP server (wernerpe/mcpacer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCPacer, 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.
32 MCPacer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.