agent_permission_vault
Enforce scoped permissions for autonomous agents before external actions.
When an agent should call it
Check owner-configured grants, denies, approvals, capability/resource scopes, expiry, environment and severity. Explicit deny overrides approval and allow; approval overrides allow; no matching rule returns UNKNOWN. Agent-facing operation is check-only; owner policy changes require authenticated controls. This is authorization, not action safety.
Input: Check capability, resource, scope, and optional environment/severity context
Price: $0.001 USDC per call, paid in USDC via x402 on Base.
MCP connection: one-time setup, then call agent_permission_vault on each needed workflow.
Direct HTTP resource: https://mcp.dropenginehq.com/api/permission-vault
Example input
{
"operation": "check",
"capability": "send_email",
"resource": "customer-support",
"scope": "support-agent",
"context": {
"environment": "production"
}
}Each call requests payment for this tool only. The agent receives a structured result and decides what to do next. Check the limits above before acting on risk, market, freshness, or availability results.
MCP endpoint: https://mcp.dropenginehq.com/api/agent-services