Mark an event as processed so it no longer appears in poll_events
AI agents use acknowledge_event to create or update resources in ClawDaemon MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ClawDaemon MCP environment.
This tool updates the state of an event record by marking it as processed. It is a reversible metadata write operation (changing a flag/status) with no destructive, financial, or execution implications. The blast radius is low — misuse could cause events to be skipped in processing pipelines, but the data itself is not deleted.
From the tool's definition Mark an event as processed so it no longer appears in poll_events
Attacks that exploit this kind of access
Mark an event as processed so it no longer appears in poll_events. It is categorised as a Write tool in the ClawDaemon MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ClawDaemon MCP server in PolicyLayer and add a rule for acknowledge_event: 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 ClawDaemon MCP. Nothing to install.
acknowledge_event is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the acknowledge_event 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 acknowledge_event. 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.
acknowledge_event is provided by the ClawDaemon MCP server (mordiaky/clawdaemon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →