> ## Documentation Index
> Fetch the complete documentation index at: https://docs.veto.tools/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> What Veto is, why it exists, and how it fits into an AI agent stack.

Veto is a runtime authorization service for AI agents. It sits between your agent and the tools it calls, evaluates every action against the policies you define, and decides: **allow** or **deny** — in under 10ms, at the edge.

## The problem

Identity protocols like MCP and OAuth answer one question: *who is this agent?* They don't answer the harder question: *what should this agent be allowed to do?*

An authenticated agent can still send emails it shouldn't send, delete records it shouldn't delete, or call external APIs at unbounded rates. Authentication is a prerequisite — it's not authorization.

Veto fills that gap.

## How it fits

Every tool call your agent makes passes through Veto before it executes:

```
Agent → Veto (authorized?) → Tool execution
```

If a matching policy allows the action, it proceeds. If nothing allows it, it's blocked. There is no implicit trust — the default posture is deny.

## Key concepts

**Agents** are the AI actors you register with Veto — bots, workflows, or models that call tools on behalf of users or systems. Each agent has a stable ID used in authorization checks.

**Policies** are the rules that govern what an agent can do. A policy is a named set of rules attached to an agent. Rules can express allowlists, denylists, parameter constraints, rate limits, and time-based windows.

**Authorization checks** are the calls your code makes to Veto at runtime — one per tool invocation. Veto evaluates the matching policies and returns a decision with a reason.

**Audit log** is the complete record of every decision Veto has made. Every authorization check — allowed or denied — is logged and queryable, giving you a full trail of agent behavior.

## What you get

<CardGroup cols={2}>
  <Card title="Sub-10ms decisions" icon="bolt">
    Powered by Cloudflare Workers with global distribution. Authorization adds no meaningful latency to your tool calls.
  </Card>

  <Card title="Default-deny posture" icon="shield">
    No matching policy means blocked. You opt in to what's allowed — not what's denied.
  </Card>

  <Card title="Full audit trail" icon="list">
    Every check is logged with the outcome, matched policy, reason, and latency. Query it from the dashboard or API.
  </Card>

  <Card title="Node.js and Python SDKs" icon="code">
    Typed clients for both languages. One method call to authorize a tool call.
  </Card>

  <Card title="MCP-native middleware" icon="plug">
    Drop-in guard and middleware helpers for Model Context Protocol servers.
  </Card>

  <Card title="Five rule types" icon="list-checks">
    Tool allowlists, denylists, parameter constraints, rate limits, and time-based windows.
  </Card>
</CardGroup>

## Next step

<Card title="Quick Start" icon="rocket" href="/quickstart">
  Make your first authorization check in under 5 minutes.
</Card>