This record as markdown: /tools/openclaw/new.md
What new does on OpenClaw
AI agents invoke new 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 new is rated High
Resetting a session is an execute action: it runs a command that triggers system state changes. The effect is not purely data retrieval (Read), not reversible user data modification (Write), and not permanent deletion (Destructive). However, it does execute logic with side effects that could disrupt ongoing work, access control, or agent state.
From the tool's definition Tool description explicitly states 'Reset the session (/reset)' — this triggers an external operation (session reset) whose effects depend on the context and state being reset.
Attacks that exploit this kind of access
The rule that runs new 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 new, this is the rule to start with:
new 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 new call is checked against it from then on.
Questions about new
Reset the session (/reset). 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 new: 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.
new 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 new 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 new. 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.
new 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