AI agents invoke restart_kernel to trigger actions in Ast Editor. 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.
Restarting a kernel stops and restarts a running process, clearing its state and potentially interrupting ongoing operations. This is an Execute-category action because it triggers an external computational operation whose effects depend on the kernel state and running code.
From the tool's definition Tool name 'restart_kernel' indicates triggering an external operation (kernel restart). Server context describes 'editing files surgically via Abstract Syntax Trees' and 'AI coding agents,' suggesting the kernel likely refers to a code execution/Jupyter…
Documented attack patterns abuse exactly the kind of access restart_kernel gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ast Editor, and nothing reaches the server without passing your rules. This is the rule we recommend for restart_kernel:
{
"version": "1",
"default": "deny",
"tools": {
"restart_kernel": {
"limits": [
{
"counter": "restart_kernel_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}restart_kernel stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
restart_kernel. It is categorised as a Execute tool in the Ast Editor MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ast Editor MCP server in PolicyLayer and add a rule for restart_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 Ast Editor. Nothing to install.
restart_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 restart_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 restart_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.
restart_kernel is provided by the Ast Editor MCP server (kambleakash0/agent-skills). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ast Editor, 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.
59 Ast Editor tools catalogued and risk-classified — across an index of 43,000+ MCP servers.