Check your inbox for messages from other agents. Call this at the START of any task and PERIODICALLY during long work. If you have messages, read them and reply or acknowledge before continuing.
AI agents call peek to retrieve information from Claude Intercom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads/fetches messages from an inbox without creating, modifying, or deleting data. It is a passive inspection operation analogous to listing or getting messages, placing it firmly in the Read category with low severity.
From the tool's definition "Check your inbox for messages from other agents" — retrieves/queries incoming messages with no side effects described
Attacks that exploit this kind of access
Check your inbox for messages from other agents. Call this at the START of any task and PERIODICALLY during long work. If you have messages, read them and reply or acknowledge before continuing. It is categorised as a Read tool in the Claude Intercom MCP Server, which means it retrieves data without modifying state.
Register the Claude Intercom MCP server in PolicyLayer and add a rule for peek: 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.
peek 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 peek 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 peek. 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.
peek 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 →