AI agents invoke jupyter_start_kernel to trigger actions in XLMCP. 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.
jupyter_start_kernel triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
Start a new Jupyter kernel. It is categorised as a Execute tool in the XLMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the XL MCP server in PolicyLayer and add a rule for jupyter_start_kernel: 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 XLMCP. Nothing to install.
jupyter_start_kernel 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 jupyter_start_kernel 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 jupyter_start_kernel. 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.
jupyter_start_kernel is provided by the XL MCP server (xlydiansoftware/aix). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.