AI agents use cancel-async-job to create or update resources in Cross-LLM MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cross-LLM MCP Server environment.
Cancelling an async job modifies the state of a job (from pending/processing to cancelled). This is a reversible state change in the sense that it doesn't permanently delete data, but it does terminate an ongoing operation. It fits best under Write as it modifies job state. The blast radius is medium since cancelling the wrong job could disrupt LLM inference workflows but does not destroy data or move money.
From the tool's definition Cancel a pending or processing async job
Documented attack patterns abuse exactly the kind of access cancel-async-job gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cross-LLM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for cancel-async-job:
{
"version": "1",
"default": "deny",
"tools": {
"cancel-async-job": {
"limits": [
{
"counter": "cancel-async-job_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}cancel-async-job stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Cancel a pending or processing async job. It is categorised as a Write tool in the Cross-LLM MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cross-LLM MCP Server MCP server in PolicyLayer and add a rule for cancel-async-job: 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 Cross-LLM MCP Server. Nothing to install.
cancel-async-job is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cancel-async-job 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 cancel-async-job. 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.
cancel-async-job is provided by the Cross-LLM MCP Server MCP server (jamesanz/cross-llm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cross-LLM MCP Server, 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.
23 Cross-LLM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.