List a day's attendance exceptions — missing punches, lates, absences (scenario 9).
AI agents call get_daily_exceptions to retrieve information from Attendance without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays attendance exception data (missing punches, lates, absences) without creating, modifying, or deleting any records. It is a passive read operation with no side effects. Severity is low because the output is internal HR/attendance metadata with limited blast radius if accessed inappropriately.
From the tool's definition Tool name 'get_daily_exceptions' and description 'List a day's attendance exceptions' indicate a query/retrieval operation. No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
List a day's attendance exceptions — missing punches, lates, absences (scenario 9). It is categorised as a Read tool in the Attendance MCP Server, which means it retrieves data without modifying state.
Register the Attendance MCP server in PolicyLayer and add a rule for get_daily_exceptions: 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 Attendance. Nothing to install.
get_daily_exceptions 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 get_daily_exceptions 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 get_daily_exceptions. 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.
get_daily_exceptions is provided by the Attendance MCP server (wenmaubipo/attendance-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 →