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

# Loqate for AI Agents

> Verify addresses, emails, and phone numbers from agentic systems — with confidence scores, policy-aware recommendations, and full audit trails.

**Integrate Loqate into AI agents, LLM tool loops, and automated workflows.**

Loqate for Agents provides developer tools purpose-built for agentic systems. Verify contact data in real time with deterministic scoring, policy-driven decisioning, and structured output that agents can act on without human intervention.

<CardGroup cols={2}>
  <Card title="Overview" icon="robot" href="/ai-agents/overview">
    What is Reach and how it fits into agentic workflows
  </Card>

  <Card title="Quick Start" icon="rocket" href="/ai-agents/quickstart">
    Install the CLI and run your first verification in under 2 minutes
  </Card>

  <Card title="CLI Reference" icon="terminal" href="/ai-agents/cli/installation">
    Install and use the `lqt` command-line tool
  </Card>

  <Card title="MCP Server" icon="plug" href="/ai-agents/mcp/overview">
    Connect Loqate to Claude, Cursor, VS Code, and other MCP clients
  </Card>

  <Card title="Policies" icon="shield-halved" href="/ai-agents/reference/policies">
    Built-in and custom policy frameworks for decisioning
  </Card>

  <Card title="Configuration" icon="gear" href="/ai-agents/reference/configuration">
    Authentication, environment variables, and key resolution
  </Card>
</CardGroup>

***

## Why Loqate for Agents?

Traditional verification APIs return raw data that requires human interpretation. Loqate for Agents wraps verification in a decisioning layer — every response includes a confidence score (0–1), a policy-aware recommendation (`accept`, `review`, or `reject`), and a match-level assessment. This means your agent can make decisions autonomously based on structured, deterministic output.

* **Deterministic scoring** — same input, same score, every time, across CLI, MCP, and API
* **Policy-driven decisions** — four built-in policies (strict, shipping, standard, permissive) plus custom policy support
* **Agent-native interfaces** — CLI for tool loops, MCP for direct agent integration, JSON output for pipelines
* **245+ countries and territories** supported
* **No new contract required** — uses your existing Loqate API key

<Tip>
  Visit [agents.gbg.com/reach.html](https://agents.gbg.com/reach.html) for product information, demos, and the latest updates on Reach.
</Tip>