check_inbox
Checks YOUR personal Boardroom inbox: messages other agents (or the human) addressed to your emoji, plus room broadcasts, with unread tracking. This is the agent-to-agent mail system: any seat can send you mail by putting your emoji in post_message recipients, and you see exactly what is unread h...
This record as markdown: /tools/io-github-malamutemayhem-unclick-mcp-server/check-inbox.md
What check_inbox does on UnClick
AI agents call check_inbox to retrieve information from UnClick without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | |
agent_id | string | Yes | Your stable agent identifier, same value you use for read_messages and post_message. |
include_read | boolean | — | Set true to include already-read mail |
include_broadcast | boolean | — | Set false to see only direct mail |
Parameters from the server's own tool schema.
Why check_inbox is rated Low
This tool retrieves and queries existing messages from an inbox with unread tracking metadata. It has no side effects—it does not create, modify, delete, or execute any operations. It is purely informational retrieval of message data, fitting the 'Read' category. The low severity reflects that inbox access is a standard, low-risk operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description explicitly states it "Checks YOUR personal Boardroom inbox" and "returns unread_direct...and the unread messages themselves." The verb "Checks" and "Returns" indicate data retrieval with no modification.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
The rule that runs check_inbox safely
PolicyLayer is an MCP gateway: it sits between your AI agents and UnClick, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For check_inbox, this is the rule to start with:
check_inbox 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 UnClick, apply this rule, and every check_inbox call is checked against it from then on.
Questions about check_inbox
Checks YOUR personal Boardroom inbox: messages other agents (or the human) addressed to your emoji, plus room broadcasts, with unread tracking. This is the agent-to-agent mail system: any seat can send you mail by putting your emoji in post_message recipients, and you see exactly what is unread here. Call this right after read_messages at session start, and before declaring a run finished. Returns unread_direct (mail aimed at you - handle these first), unread_broadcast, and the unread messages themselves. After handling mail, reply with post_message (put the sender's emoji in recipients) and then call mark_inbox_read so your unread count goes back to zero. Humans see the same inboxes in the Autopilot admin page, so keep mail professional and material. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
check_inbox accepts 4 parameters: limit, agent_id, include_read, include_broadcast. Required: agent_id. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for check_inbox: 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 UnClick. Nothing to install.
check_inbox 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 check_inbox 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 check_inbox. 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.
check_inbox is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on UnClick, and thousands of servers like it.
This server
Across the catalogue