This record as markdown: /tools/openclaw/command.md
What command does on OpenClaw
AI agents invoke command 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 command is rated High
A tool that runs arbitrary shell commands has an extremely high blast radius. An AI agent could execute any system-level operation, including data destruction, network access, privilege escalation, or exfiltration. This is the most dangerous Execute-class tool possible, warranting critical severity.
From the tool's definition Tool name 'command', description 'Shell command' — directly executes shell commands on the host system.
Attacks that exploit this kind of access
The rule that runs command 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 command, this is the rule to start with:
command 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 command call is checked against it from then on.
Questions about command
Shell command. 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 command: 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.
command 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 command 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 command. 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.
command 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