Critical Risk →

cancel_compel

Cancel an in-progress compel. Dequeues it if still queued, otherwise cancels any active external (AI provider) tasks and transitions it to CANCELLED. Idempotent - cancelling an already-CANCELLED compel succeeds. Use to stop a mis-prompted or runaway job before it consumes more render minutes.

Part of the Compeller server.

cancel_compel can permanently delete data in Compeller, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE COMPELLER →

Free to start. No card required.

AI agents may call cancel_compel to permanently remove or destroy resources in Compeller. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. PolicyLayer blocks destructive tools by default and requires explicit human approval before enabling them.

Without a policy, an AI agent could call cancel_compel in a loop, permanently destroying resources in Compeller. There is no undo for destructive operations. PolicyLayer blocks this tool by default and only allows it when a human explicitly approves the action.

Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "cancel_compel"
  ]
}

See the full Compeller policy for all 30 tools.

Get this rule live on your own Compeller server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY COMPELLER →

View all 30 tools →

These attack patterns abuse exactly the kind of access cancel_compel gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so cancel_compel only ever does what you allow.

SECURE COMPELLER →

Other destructive tools across the catalogue. The same approach applies to each: deny by default, or require human approval.

What does the cancel_compel tool do? +

Cancel an in-progress compel. Dequeues it if still queued, otherwise cancels any active external (AI provider) tasks and transitions it to CANCELLED. Idempotent - cancelling an already-CANCELLED compel succeeds. Use to stop a mis-prompted or runaway job before it consumes more render minutes.. It is categorised as a Destructive tool in the Compeller MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on cancel_compel? +

Register the Compeller MCP server in PolicyLayer and add a rule for cancel_compel: 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 Compeller. Nothing to install.

What risk level is cancel_compel? +

cancel_compel is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit cancel_compel? +

Yes. Add a rate_limit block to the cancel_compel 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.

How do I block cancel_compel completely? +

Set action: deny in the PolicyLayer policy for cancel_compel. 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.

What MCP server provides cancel_compel? +

cancel_compel is provided by the Compeller MCP server (https://compeller.ai/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Compeller tool call.

Deterministic rules across all 30 Compeller tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.