AI agents invoke cancel_server to trigger actions in Llauncher. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool interrupts/cancels an ongoing operation (start or swap of a server instance). It triggers an external operation that affects running processes, making it Execute. It is not purely destructive (no data deletion) but has real side effects on server lifecycle state. Misuse could abort legitimate inference server operations, causing service disruption.
From the tool's definition Cancel an in-flight start or swap on this port
Attacks that exploit this kind of access
Cancel an in-flight start or swap on this port (ADR-014). It is categorised as a Execute tool in the Llauncher MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Llauncher MCP server in PolicyLayer and add a rule for cancel_server: 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 Llauncher. Nothing to install.
cancel_server is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cancel_server 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_server. 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_server is provided by the Llauncher MCP server (shanevcantwell/llauncher). 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 →