[Integrations](https://spiral.ai/integrations) › [goose](https://spiral.ai/integrations/goose) › [OpenAddresses address points](https://spiral.ai/integrations/goose/openaddresses-address-points)

# How to Use OpenAddresses address points in goose

Returns pages of address rows from one geographic source, pinned to one processing job. Use it to build a local address index or collect points within a geographic area.

|  |  |
| --- | --- |
| Model | OpenAddresses address points |
| Available through | Alexandria |
| Category | Listings |
| Price | $0.00873 per call. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with OpenAddresses address points in goose

- Use OpenAddresses address points to collect a sample from us/ak/bristol_bay_borough, then compare its returned address components with this project's database schema.
- Use OpenAddresses address points to look this up and give me the result as a table. Save the result in ./assets.
- Pull the latest numbers from OpenAddresses address points and tell me what changed since last week.
- Check OpenAddresses address points and summarize what you find in three bullet points.
- Pull the newest data from OpenAddresses address points and give me the result as a table.

## How to set up OpenAddresses address points in goose

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the extension**: In goose Desktop, open the sidebar, click Extensions, then Add custom extension. Enter:

2. **Sign in**: When goose first connects to Spiral, your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key. If the browser does not open, goose prints the link to open yourself.

### Use the Spiral skill

1. **Send goose this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run OpenAddresses address points**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "batch-openaddresses-io/addresses/records_list",
    "input": {
      "source": "<source>"
    }
  }'
```

Then paste one of the prompts above: goose finds OpenAddresses address points on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/goose

## OpenAddresses address points tools and prices

- [OpenAddresses per-source runs · Records list](https://spiral.ai/tools/alexandria/batch-openaddresses-io/addresses/records_list) (Alexandria): $0.00873 per call.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| bbox |  | — | Bounding box `[west, south, east, north]` in WGS84 degrees. |
| name |  | — | Coverage name when a source has more than one data entry per layer (e.g. `us/mn/statewide` addresses has `default` and `state`); the function says so when it is needed. |
| layer | addresses, buildings, parcels, centerlines | addresses | OpenAddresses layer of the source. This program shapes `addresses` rows; other layers are listed and status-checked but their records are not decoded. |
| cursor |  | — | Opaque `next_cursor` from the previous page. Carries the pinned job id, ETag, mode and position; other inputs must match the first call. |
| page_size | 1 to 1000 | 500 | Rows per page in whole-file mode (tile mode returns one z14 tile per page). |

## What can you do with OpenAddresses address points in goose?

Build a local address index with a defined OpenAddresses publication behind each import. A coding agent can inspect geographic sources, compare processing history, and examine address rows while adapting the project's geocoding code.

### Build a local geocoding index

Find a geographic source, check its publication, and collect its address points. Inspect selected rows before importing street numbers, street names, and coordinates into a local search index.

### Assess coverage for a municipal map

Discover county and statewide sources, inspect their available publications, and collect points for the map area. Reread sample rows to check the address components your map needs.

### Investigate an address count drop

Use job history to locate a count change, then inspect the current publication and its address rows. Reread examples from the collected output to help distinguish processing problems from changes in the available data.

### Prepare an address extract for reuse

Find a source and review its license classification before selecting a publication. Collect the address extract and inspect sample records alongside the original source's reuse terms.

### Create a reproducible geocoding benchmark

Choose an available processing job and collect its address rows as a benchmark dataset. Reread selected records from that publication when investigating changes in a geocoder's results.

### Compare address sources for a region

List geographic sources, compare their publication details and processing histories, and examine address samples. Use the results to choose which source to evaluate for a regional mapping project.

## Overview

- [Alexandria](https://spiral.ai/providers/alexandria)
- [All goose guides](https://spiral.ai/integrations/goose)

## OpenAddresses address points in other agents

- [Amp](https://spiral.ai/integrations/amp/openaddresses-address-points)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/openaddresses-address-points)
- [Claude](https://spiral.ai/integrations/claude-desktop/openaddresses-address-points)
- [Claude Code](https://spiral.ai/integrations/claude-code/openaddresses-address-points)
- [Cline](https://spiral.ai/integrations/cline/openaddresses-address-points)
- [Codex](https://spiral.ai/integrations/codex/openaddresses-address-points)
- [Cursor](https://spiral.ai/integrations/cursor/openaddresses-address-points)
- [Devin](https://spiral.ai/integrations/devin/openaddresses-address-points)
- [dots](https://spiral.ai/integrations/dots/openaddresses-address-points)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/openaddresses-address-points)
- [Gemini](https://spiral.ai/integrations/gemini/openaddresses-address-points)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/openaddresses-address-points)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/openaddresses-address-points)
- [Grok](https://spiral.ai/integrations/grok/openaddresses-address-points)
- [Grok Build](https://spiral.ai/integrations/grok-build/openaddresses-address-points)
- [Hermes](https://spiral.ai/integrations/hermes/openaddresses-address-points)
- [Instinct](https://spiral.ai/integrations/instinct/openaddresses-address-points)
- [Manus](https://spiral.ai/integrations/manus/openaddresses-address-points)
- [Muse](https://spiral.ai/integrations/muse/openaddresses-address-points)
- [Muse Code](https://spiral.ai/integrations/muse-code/openaddresses-address-points)
- [n8n](https://spiral.ai/integrations/n8n/openaddresses-address-points)
- [Notion](https://spiral.ai/integrations/notion/openaddresses-address-points)
- [OpenClaw](https://spiral.ai/integrations/openclaw/openaddresses-address-points)
- [opencode](https://spiral.ai/integrations/opencode/openaddresses-address-points)
- [Perplexity](https://spiral.ai/integrations/perplexity/openaddresses-address-points)
- [Raycast](https://spiral.ai/integrations/raycast/openaddresses-address-points)
- [VS Code](https://spiral.ai/integrations/vscode/openaddresses-address-points)
- [Windsurf](https://spiral.ai/integrations/windsurf/openaddresses-address-points)
- [Zapier](https://spiral.ai/integrations/zapier/openaddresses-address-points)

## More goose guides

- [New Orleans permit search](https://spiral.ai/integrations/goose/new-orleans-permit-search)
- [OpenAddresses address record](https://spiral.ai/integrations/goose/openaddresses-address-record)
- [New Orleans permit details](https://spiral.ai/integrations/goose/new-orleans-permit-details)
- [OpenAddresses source catalog](https://spiral.ai/integrations/goose/openaddresses-source-catalog)
- [New Orleans contractor activity](https://spiral.ai/integrations/goose/new-orleans-contractor-activity)
- [OpenAddresses source history](https://spiral.ai/integrations/goose/openaddresses-source-history)

## Questions about OpenAddresses address points in goose

**Can goose use OpenAddresses address points?**

Yes. Add Spiral to goose as an MCP server, and goose can find and run OpenAddresses address points like any built-in tool.

**How much does OpenAddresses address points cost in goose?**

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your goose plan is separate.

**Do I need an Alexandria account to use OpenAddresses address points in goose?**

No. Spiral runs OpenAddresses address points on its own Alexandria account. You sign in to Spiral once and never paste a key.

**How long does it take to set up OpenAddresses address points in goose?**

About two minutes: add the extension, then sign in.

**Does goose wait while OpenAddresses address points runs?**

OpenAddresses address points runs in the background. goose starts the run, checks on it and gives you the json when it's ready.

**Where does OpenAddresses get its data?**

OpenAddresses collects authoritative geographic data from existing publishers. It does not create its own address data.

**Is OpenAddresses limited to US addresses?**

No. OpenAddresses includes geographic sources from around the world, so research can extend beyond US counties and states.

**How often is OpenAddresses refreshed?**

Its processing library runs the dataset weekly and on demand. That schedule describes OpenAddresses processing, not how often an original publisher edits its address records.

**Are all address coordinates equally precise?**

OpenAddresses defines accuracy categories that include interpolation, coded 4, and unknown accuracy, coded 5. Those categories make a blanket rooftop-accuracy assumption inappropriate.

**Does one license cover every OpenAddresses dataset?**

Each source retains its own license. For example, the San Francisco address source specifies PDDL 1.0, so reuse terms need to be checked for the geographic source you select.

