Build with AI

Drop Ideal Postcodes into any AI workflow, from coding agents driving a repo to chat-driven app builders generating a frontend.

Quick start

Give your agent the docs. Paste llms.txt into the model's context.
Get an API key.
- Quick test: use ak_test. Public, capped at 5 lookups/day, will break in production.
- Real testing: sign up for a free trial key with a real test balance. There are three ways to sign up: MCP (coming soon), CLI (idpc keys create) or the web dashboard.
Lock it down before going live. Restrict the key to your origin via Allowed URLs.

Ordered by what an agent should reach for first.

llms.txt: full API reference, integration guides and widget docs as one file. Paste into a model's context, or wire into a docs MCP server like Context7.
MCP server: coming soon. Will surface API docs, dataset metadata and key management as MCP tools.
CLI: npm install -g @ideal-postcodes/cli. Built for agents: JSON output in non-TTY, stable exit codes, no interactive prompts under pipes. Subcommands: auth, keys, cleanse, find, lookup. Use a backend key (no Allowed URLs).
Address Finder: address autocomplete widget. Works in the UK and internationally. Use when users type the address directly into the form.
Postcode Lookup: postcode → address dropdown. Supports countries with efficient postcode systems (UK, Ireland, Singapore, Netherlands). Use when users enter a postcode first.
Per-page markdown: append .md to any docs URL for the plain-text version (e.g. /docs/address-finder.md).

Per-platform setup, prompts and key-storage instructions live in Build with AI integrations.