Poll an approval
AI agents call check_approval to retrieve information from Audit event mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries approval status data with no side effects—it polls existing data rather than creating, modifying, or deleting records. It is the least severe category and poses minimal risk even if misused by an AI agent, as it only observes approval state without taking action.
From the tool's definition Tool name 'check_approval' and description 'Poll an approval' indicate a read-only query operation that retrieves the status of a previously-requested approval without modifying state.
Attacks that exploit this kind of access
Poll an approval. It is categorised as a Read tool in the Audit event mcp MCP Server, which means it retrieves data without modifying state.
Register the Audit event MCP server in PolicyLayer and add a rule for check_approval: 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 Audit event mcp. Nothing to install.
check_approval 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_approval 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_approval. 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_approval is provided by the Audit event MCP server (mightbesaad/audit-event-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 →