Skip to content
Lootrunners
Built for agents

One spend interface for every agent.

Your agent requests spend. Lootrunners handles policy, approvals, execution, evidence, and accounting behind a bounded API or MCP connection.

MCPRESTWEBHOOKS

Agent credentials cannot manage budgets, policies, or treasury settings.

const res = await fetch('https://app.lootrunners.com/api/agent/v1/spend/intents', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${LOOTRUNNERS_AGENT_KEY}`,
    'Idempotency-Key': `lead-${lead.id}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    mandate_id: 'midwest-research',
    purpose: 'Verify employer and title',
    amount_usd: '0.08',
    vendor_domain: 'example-data.com',
  }),
});

// decision.result is AUTO, ASK, or BLOCK
const { decision } = await res.json();
return decision.result;
01
Request

The agent declares purpose, amount, and service against its mandate. Idempotency keys make retries safe.

02
Decision

AUTO executes, ASK routes to a person, BLOCK returns a machine-readable denial reason the agent can act on.

03
Evidence

The agent attaches outputs; webhooks stream settlement and fulfillment events into your own systems.

Bounded MCP tools
request_spendget_spend_statusget_spend_contextsearch_paid_servicessubmit_outcomerequest_exceptionset_budgetedit_policy

Deliberately bounded authority: no tool lets an agent widen its own limits.

Wire one agent to the sandbox in an afternoon.

Try the sandbox
© 2026 LootrunnersHomeSecurityPricing