This record as markdown: /tools/openclaw/events-poll.md
What events_poll does on OpenClaw
AI agents call events_poll to retrieve information from OpenClaw without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why events_poll is rated Low
This tool queries or retrieves conversation events from a queue using a cursor position. It has no side effects on the data being read, does not modify or delete events, and does not execute external operations. It is purely a data retrieval mechanism, fitting the Read category.
From the tool's definition "Poll queued OpenClaw conversation events since a cursor" — the verb 'poll' and phrase 'since a cursor' indicate retrieval of existing queued events without modification or deletion.
Attacks that exploit this kind of access
The rule that runs events_poll 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 events_poll, this is the rule to start with:
events_poll is read-only, so it stays allowed. 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 events_poll call is checked against it from then on.
Questions about events_poll
Poll queued OpenClaw conversation events since a cursor. It is categorised as a Read tool in the OpenClaw MCP Server, which means it retrieves data without modifying state.
Register the OpenClaw MCP server in PolicyLayer and add a rule for events_poll: 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.
events_poll is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the events_poll 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 events_poll. 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.
events_poll 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.
This server
Across the catalogue