canonical: https://jentic.com/apis/smarty.com/us-extract-api

# Smarty US Extract API

The US Extract API extracts, validates, and standardizes addresses from unstructured text. It can process text containing one or more addresses and return structured, USPS-standardized address data. The API exposes 1 endpoints secured with apiKey authentication.

## For AI agents

Programmatically extract addresses from text. Covers 1 operations with apiKey authentication.

## Scope

Does not handle payments, communications, or crm - use for developer tools only.

## Capabilities

- Extract addresses from text
- Manage developer tools data programmatically
- Integrate US Extract API into automated workflows
- Query and filter US Extract API records by parameters
- Monitor US Extract API operational status and events

## Use cases

### Developer Tools Operations

Use the US Extract API to perform developer tools operations programmatically. The API provides 1 endpoints covering core functionality including extract addresses from text.

Example prompt: Call POST / to extract addresses from text

### AI Agent Integration via Jentic

AI agents discover and call US Extract API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.

Example prompt: Search Jentic for 'extract addresses from text', load the operation schema, and execute with Jentic-managed credentials

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | / | Extract addresses from text |

## Key resources

- **Extract** — Address extraction operations

## Why Jentic

- **Setup:** Wiring the US Extract API by hand means passing its auth-id key on the query string against us-extract.api.smarty.com and managing retries yourself. Through Jentic you install once, import the US Extract API from the API Directory, store the key once, and your agent calls it.
- **Permission scoping:** US Extract exposes a single extract operation that takes text in the request body rather than a path-scoped resource, so scope the agent to just that extract operation. You choose which operations are allowed, so nothing beyond address extraction runs unless you add it.
- **Credential handling:** Your Smarty key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'extract addresses from text', and Jentic returns the matching US Extract operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Github** — Alternative developer tools API
- **Gitlab** — Alternative developer tools API

## FAQ

### What authentication does the US Extract API use?

The US Extract API uses an API key passed in the `auth-id` query. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.

### Can I extract addresses from text with the US Extract API?

Yes. Use the POST / endpoint. The API returns structured JSON responses that agents can parse and act on directly.

### What are the rate limits for the US Extract API?

Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.

### How do I extract addresses from text through Jentic?

Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'extract addresses from text'. Jentic returns the matching US Extract API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.

### How many endpoints does the US Extract API have?

The US Extract API exposes 1 endpoints covering extract operations.

### Can I limit what my agent is allowed to do with the US Extract API?

Yes. Because you run Jentic One yourself, your own rules decide which operations and credentials the agent may use. The US Extract API exposes a single extract operation (POST /) that takes text in the request body, so you can scope the agent to just that address-extraction call. Nothing beyond extracting addresses from text runs unless you explicitly allow it.