Check who hasn't submitted their weekly reports yet
AI agents call check_missing_reports to retrieve information from Weekly Report Checker 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 information about missing report submissions. It has no side effects, does not modify data, and does not execute external operations beyond querying a data source. This is a classic Read operation—it searches/lists entities (people with missing reports) for informational purposes only.
From the tool's definition Tool description states 'Check who hasn't submitted their weekly reports yet' - a retrieval operation that queries submission status without modifying data.
Attacks that exploit this kind of access
Check who hasn't submitted their weekly reports yet. It is categorised as a Read tool in the Weekly Report Checker MCP Server, which means it retrieves data without modifying state.
Register the Weekly Report Checker MCP server in PolicyLayer and add a rule for check_missing_reports: 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 Weekly Report Checker. Nothing to install.
check_missing_reports 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_missing_reports 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_missing_reports. 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_missing_reports is provided by the Weekly Report Checker MCP server (kaneyxx/weekly-report-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 →