This record as markdown: /tools/openclaw/restart.md
What restart does on OpenClaw
AI agents invoke restart to trigger actions in OpenClaw. 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.
Why restart is rated High
This tool executes a restart operation on a gateway component, which is a significant system-level action. It triggers an external operation that interrupts service, though it is reversible in principle (a restart does not destroy data). This places it in Execute rather than Destructive. The high severity reflects the potential for service disruption and the blast radius if an AI agent incorrectly triggers this.
From the tool's definition Tool name 'restart' with description 'Restart the gateway (if enabled)' indicates triggering an external operation (gateway restart) whose effects depend on system state and cannot be easily undone.
Attacks that exploit this kind of access
The rule that runs restart safely
PolicyLayer is an MCP gateway: it sits between your AI agents and OpenClaw, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For restart, this is the rule to start with:
restart 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.
The button opens the PolicyLayer dashboard: create your workspace, connect OpenClaw, apply this rule, and every restart call is checked against it from then on.
Questions about restart
Restart the gateway (if enabled). It is categorised as a Execute tool in the OpenClaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenClaw MCP server in PolicyLayer and add a rule for restart: 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 OpenClaw. Nothing to install.
restart 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 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. 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 is provided by the OpenClaw MCP server (openclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on OpenClaw, and thousands of servers like it.
Across the catalogue