This record as markdown: /tools/openclaw/stop.md
What stop does on OpenClaw
AI agents invoke stop 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 stop is rated High
This tool executes an action (stopping a run) that has external effects on a running process or operation. While not destructive (data is not deleted), it is an Execute-category tool because it performs a state-changing action triggered by the tool's invocation.
From the tool's definition Tool description states 'Stop the current run', indicating it triggers an operation that interrupts or terminates an active process.
Attacks that exploit this kind of access
The rule that runs stop 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 stop, this is the rule to start with:
stop 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 stop call is checked against it from then on.
Questions about stop
Stop the current run. 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 stop: 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.
stop 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 stop 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 stop. 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.
stop 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