Ask a human to approve an action before it runs. Creates a pending approval, witnesses it as an approval.requested chain event, and returns approvalId, approvalUrl (one-tap approve page), and webhookSecret. Outcomes are approved | denied | timeout — poll with check_approval, or receive the signed...
AI agents use request_approval to create or update resources in Audit event mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Audit event mcp environment.
This tool creates a new approval record and logs a chain event — a reversible write operation. It does not execute the underlying action itself, just requests human sign-off. Misuse could flood humans with spurious approval requests or be used to social-engineer approvals for sensitive actions, giving it medium severity.
From the tool's definition Creates a pending approval, witnesses it as an approval.requested chain event, and returns approvalId, approvalUrl, and webhookSecret
Attacks that exploit this kind of access
Ask a human to approve an action before it runs. Creates a pending approval, witnesses it as an approval.requested chain event, and returns approvalId, approvalUrl (one-tap approve page), and webhookSecret. Outcomes are approved | denied | timeout — poll with check_approval, or receive the signed decision webhook at callbackUrl. It is categorised as a Write tool in the Audit event mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Audit event MCP server in PolicyLayer and add a rule for request_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.
request_approval is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the request_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 request_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.
request_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 →