Call at the start of every session to catch up on what happened since the user last chatted. Returns unread signals from TestPass, Crews, Memory, and every UnClick tool. Narrate the important ones to the user in plain English. Automatically marks them as read so you do not re-narrate later.
AI agents call check_signals to retrieve information from UnClick without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
agent_id | string | — | Stable Boardroom agent_id for read attribution, e.g. chatgpt-codex-worker2. |
Parameters from the server's own tool schema.
This tool retrieves and displays information (signals from various sources) without creating, modifying, deleting, executing external commands, or affecting financial data. The marking-as-read operation is a reversible state change on notifications, not a destructive or write operation that creates new data. It is purely informational in nature, consistent with Read category tools like fetch and query.
From the tool's definition Tool description states it 'Returns unread signals' and 'Narrate the important ones to the user in plain English. Automatically marks them as read'.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Call at the start of every session to catch up on what happened since the user last chatted. Returns unread signals from TestPass, Crews, Memory, and every UnClick tool. Narrate the important ones to the user in plain English. Automatically marks them as read so you do not re-narrate later. It is categorised as a Read tool in the UnClick MCP Server, which means it retrieves data without modifying state.
check_signals accepts 1 parameter: 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_signals: 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_signals 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_signals 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_signals. 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_signals 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.
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 →