Cancel a running async task
AI agents call async_cancel_task to permanently remove resources in MCP Async Bridge Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a running task permanently stops its execution. Unlike a pause/suspend, cancellation is typically irreversible — any partial work or state may be lost. This maps to Destructive. The blast radius is medium because it affects only a single task at a time, but the consequences (lost work, interrupted operations) can be significant depending on what the task was doing.
From the tool's definition "Cancel a running async task" — cancellation of an in-progress task is irreversible; the task's work is aborted and cannot be resumed.
Attacks that exploit this kind of access
Cancel a running async task. It is categorised as a Destructive tool in the MCP Async Bridge Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Async Bridge Server MCP server in PolicyLayer and add a rule for async_cancel_task: 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 MCP Async Bridge Server. Nothing to install.
async_cancel_task 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 async_cancel_task 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 async_cancel_task. 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.
async_cancel_task is provided by the MCP Async Bridge Server MCP server (mako10k/mcp-async). 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 →