Mark a message as read and remove it from your inbox. Use after you
AI agents call ack to permanently remove resources in Claude Intercom — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool marks a message as read AND removes it from the inbox. Removal is an irreversible action (the message is gone from the inbox permanently), which places it in the Destructive category. Severity is medium because the blast radius is limited to losing inbox messages between Claude Code instances, not broader system data, but misuse could cause agents to lose unprocessed messages they haven't acted on yet.
From the tool's definition 'remove it from your inbox' — the message is removed, which is an irreversible deletion from the inbox state
Attacks that exploit this kind of access
Mark a message as read and remove it from your inbox. Use after you. It is categorised as a Destructive tool in the Claude Intercom MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Intercom MCP server in PolicyLayer and add a rule for ack: 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 Claude Intercom. Nothing to install.
ack is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the ack 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 ack. 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.
ack is provided by the Claude Intercom MCP server (sanztheo/claude-intercom). 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 →