Integration

Add authorization to LlamaIndex agents

Wrap a LlamaIndex tool so the agent's warrant is verified before it executes — scope, spend caps, and revocation included.

Why authorize LlamaIndex tools?

LlamaIndex agents call tools to answer queries and take actions. When those tools reach production systems, you need per-agent limits enforced at call time. Wrap the tool's function with a Liceat guard and the agent's warrant becomes the contract for what it may do.

Guard a FunctionTool

import { FunctionTool } from 'llamaindex';
import { createClient, guardTool } from 'liceat';
const decide = createClient({ gateway: 'https://liceat.com' }).decider();
const search = guardTool(decide, { resource: 'mcp:search/query', action: 'read' },
  async (a) => runSearch(a.q));

FunctionTool.from((args) => search(agentWarrant, args),
  { name: 'search', description: 'Search the corpus', parameters });

What you get

• Least privilege — each agent gets a warrant scoped to exactly the tools, resources, and spend it needs.
• Provable afterward — every allow/deny is recorded in a tamper-evident log you can audit or hand to a compliance reviewer.
• Instant revocation — kill a compromised agent's authority immediately, and it cascades to every sub-agent it delegated to.
• No new keys to leak — the agent never holds your API keys, only a narrow, expiring warrant.

Frequently asked

What is Liceat?

Liceat is permission infrastructure for AI agents. You issue a warrant — a scoped, spend-capped, revocable token — that grants an agent narrow authority; the agent presents it at the point of action; Liceat enforces it (scope, spend, rate, holder-binding, revocation) and records every decision in a tamper-evident log. It is open source with a zero-dependency SDK for TypeScript and Python.

Is it free?

The SDK and self-hosted gateway are free and open source. The hosted gateway at liceat.com gives 10,000 free decisions with no card, then meters at fractions of a cent per decision — payable by card or USDC.