How to Use AFCD food search in Codex
Returns matching food entries and their Public Food Keys. Use it to find the right food description before retrieving a full nutrient profile.
Prompts to try with AFCD food search in Codex
Copy an example into Codex, or ask in your own words.
Use AFCD food search to resolve rolled oats, whole milk, and almonds for the recipe ingredient matcher in this project.
Use AFCD food search to look this up and give me the result as a table. Save the result in ./assets.
Pull the latest numbers from AFCD food search and tell me what changed since last week.
Check AFCD food search and summarize what you find in three bullet points.
Pull the newest data from AFCD food search and give me the result as a table.
How to set up AFCD food search in Codex
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the hosted server
codex mcp add spiral --url https://api.spiral.ai/mcp
- Sign in
Codex opens the browser: sign in to Spiral and click Authorize. No API key. codex mcp list then shows Spiral.
codex mcp login spiral
Use the Spiral skill
- Send Codex 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 AFCD food search
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": "afcd-foodstandards-gov-au/foods/search_foods", "input": { "page": 1 } }'
Then paste one of the prompts above: Codex finds AFCD food search on Spiral, shows the price and runs it.
AFCD food search providers and prices
Spiral runs AFCD food search through Alexandria. Open a card for today's price, with every fee included.
Settings you can ask for
Ask Codex for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Page | a number from 1 | 1 | 1-based page of the client-side paginated result (the API returns the whole list). |
| Page size | 1 to 200 | 50 | Rows per page (1-200). |
| Food group ID | a number from 1 | Restrict to one AFCD food group (see list_food_groups). | |
| Sub food group ID | a number from 1 | Restrict to one AFCD sub food group (see list_food_groups). |
Every API field of Australian Food Composition Database (AFCD, FSANZ) · Search foods is on its tool page: open its card above.
What can you do with AFCD food search in Codex?
Build an Australian food reference browser with category navigation, nutrient explanations, and food comparisons. A coding agent can use AFCD descriptions and Public Food Keys to connect search results to the correct detail records.
Compare breakfast cereals
Identify the ready-to-eat cereal category, list its foods, and resolve named cereals. Check nutrient definitions, rank the entries by iron, and inspect the selected food profiles and sampling notes.
Build a cheese reformulation reference
Find AFCD's cheese categories and enumerate the reference foods. Match named cheese types, check sodium definitions and units, then compare sodium values and inspect the underlying profiles.
Match recipe ingredients to reference foods
Map ingredients such as rolled oats, milk, and almonds to AFCD descriptions. Browse the relevant categories when names are ambiguous, then inspect preparation details and nutrient profiles before calculating recipe estimates.
Create an Australian food reference browser
Use the category hierarchy and category inventories for navigation, food search for lookup, nutrient definitions for explanations, nutrient comparisons for sorting, and individual profiles for the detail view.
Review changes to a food reference collection
Periodically compare retrieved categories, food inventories, nutrient definitions, rankings, and selected profiles with earlier observations. Produce a review queue when AFCD descriptions or values change.
Review the evidence behind category comparisons
List foods in a category, resolve ambiguous names, and inspect selected derivation and sampling notes. Explain which comparisons rely on analyzed foods and which involve calculated or borrowed data.
Compare food preparation descriptions
Find raw and cooked food entries, examine their descriptions, and compare selected nutrients using the documented definitions. Keep preparation differences explicit when presenting the results.
More on AFCD food search and Codex
Overview
AFCD food search in other agents
Questions about AFCD food search in Codex
Can Codex use AFCD food search?
Yes. Add Spiral to Codex as an MCP server, and Codex can find and run AFCD food search like any built-in tool.
How much does AFCD food search cost in Codex?
$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Codex plan is separate.
Do I need an Alexandria account to use AFCD food search in Codex?
No. Spiral runs AFCD food search on its own Alexandria account. You sign in to Spiral once and never paste a key.
How long does it take to set up AFCD food search in Codex?
About two minutes: add the hosted server, then sign in.
Does Codex wait while AFCD food search runs?
AFCD food search runs in the background. Codex starts the run, checks on it and gives you the json when it's ready.
Which foods does AFCD cover?
AFCD covers 1,588 foods commonly available in Australia. Its coverage is a reference selection of Australian foods, rather than a complete inventory of products sold worldwide.
How many nutrients can AFCD describe?
AFCD reports up to 268 nutrients per food. The nutrient documentation explains the units, derivation, assumptions, and limitations used for those components.
What changed in the latest AFCD dataset?
Release 3 incorporated new analytical data for 118 foods and an updated vitamin D dataset. That update describes the dataset as a whole; individual sampling notes provide the evidence behind a particular food.
Are all AFCD values laboratory measurements?
Laboratory analysis is the primary source, but a food's derivation can also identify calculated, borrowed, or label-based data. Sampling notes can include how many samples were purchased and where and when they were purchased.
Are nutrient comparisons based on serving size?
AFCD's nutrient comparison tables report values per 100 g. A ranking therefore compares equal food weights, which can differ substantially from the amounts someone would serve.
Start using AFCD food search in Codex
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Codex:
set up https://spiral.ai/SKILL.md


