get_coles_productsLABSCO SUMMARY
Two supermarket price lists in one answer.
Ask for a product and it comes back from both chains at once in the same shape — the comparison people normally do by flipping between two apps.
What it is
An experimental Python server that queries the product search of Australia's two big supermarkets and returns both in one consistent shape. Coles searches can be pinned to a specific store by ID, and both calls take a result limit.
What you get
- get_coles_products searches Coles by product term, optionally against a named store ID
- get_woolworths_products runs the same search against Woolworths
- Both return in the same format, so the two chains can be compared line by line rather than screen by screen
- A result limit on each call, so a broad term comes back as a shortlist rather than a catalogue
Requirements
Python 3.8 or higher and the uv package manager; run it with uv run main.py. Coles searches need an API key set in your environment or a .env file; Woolworths needs no key.
Setup effort
Build from source — clone the repository, then follow the project's own run instructions
USE CASES
Comparing a price across the two chains
One product term, both retailers, same format — the answer is the difference rather than two screenshots.
Checking what a specific branch stocks
Coles results can be pinned to a store ID, so the answer is that store's shelf rather than a national listing.
Pricing a shopping list before you leave
Run the items you care about through both chains and see where the basket lands cheaper, one product at a time.
2 tools
Listed in project docs. Your client may show a different list.
get_woolworths_productsBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
- Python 3.8 or later
- COLES_API_KEY in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
git clone https://github.com/hung-ngm/coles-woolworths-mcp-server.gitMCP Clients
Claude Desktop, Cursor
{
"mcpServers": {
"coles-woolies-mcp": {
"command": "uv",
"args": [
"run",
"--with",
"fastmcp",
"--with",
"requests",
"--with",
"python-dotenv",
"fastmcp",
"run",
"<YOUR_PATH_TO_COLES_WOOLWORTHS_MCP_SERVER>/main.py"
]
}
}
}The configuration on this page does not set COLES_API_KEY; the project's instructions put it in a .env file. Check which folder the server reads that file from before you rely on it.