How to Use OpenAddresses address record in goose
Returns one address row using a reference obtained from an address listing. Use it to inspect a selected record or reproduce a result from a particular processing job.
Prompts to try with OpenAddresses address record in goose
Copy an example into goose, or ask in your own words.
Take a row reference from an address listing for us/ak/bristol_bay_borough and use OpenAddresses address record to inspect that row before adding it as a geocoding test fixture.
Use OpenAddresses address record to look this up and give me the result as a table. Save the result in ./assets.
Pull the latest numbers from OpenAddresses address record and tell me what changed since last week.
Check OpenAddresses address record and summarize what you find in three bullet points.
Pull the newest data from OpenAddresses address record and give me the result as a table.
How to set up OpenAddresses address record in goose
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the extension
In goose Desktop, open the sidebar, click Extensions, then Add custom extension. Enter:
- 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
- Send goose this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run OpenAddresses address record
One request; the result comes back by polling or a webhook.
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_get", "input": { "hash": "<hash>", "source": "<source>" } }'
Then paste one of the prompts above: goose finds OpenAddresses address record on Spiral, shows the price and runs it.
OpenAddresses address record providers and prices
Spiral runs OpenAddresses address record through Alexandria. Open a card for today's price, with every fee included.
Settings you can ask for
Ask goose for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Layer | addresses, buildings, parcels, or centerlines | addresses | OpenAddresses layer of the source. This program shapes |
| Job ID | a number from 1 | Read this job's output instead of the latest successful one (old jobs stay readable). | |
| Occurrence | a number from 0 | 0 | 0-based index among rows sharing the hash. |
Every API field of OpenAddresses per-source runs · Records get is on its tool page: open its card above.
What can you do with OpenAddresses address record 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.
More on OpenAddresses address record and goose
Overview
OpenAddresses address record in other agents
Questions about OpenAddresses address record in goose
Can goose use OpenAddresses address record?
Yes. Add Spiral to goose as an MCP server, and goose can find and run OpenAddresses address record like any built-in tool.
How much does OpenAddresses address record 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 record in goose?
No. Spiral runs OpenAddresses address record 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 record in goose?
About two minutes: add the extension, then sign in.
Does goose wait while OpenAddresses address record runs?
OpenAddresses address record 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.
Start using OpenAddresses address record in goose
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into goose:
set up https://spiral.ai/SKILL.md


