nlace-com/mcp-supermercados-cl — explained in plain English
Analysis updated 2026-05-18
Search and compare grocery prices across five Chilean supermarket chains from an AI chat.
Build a shopping list in natural language that prioritizes your usual purchases and best prices.
Find products with the biggest current discounts that are still in stock.
Add items straight to your Jumbo cart using your existing logged in session.
| nlace-com/mcp-supermercados-cl | avijit07x/git-switch | cryptosaras/tokenward | |
|---|---|---|---|
| Stars | 54 | 54 | 54 |
| Language | TypeScript | TypeScript | TypeScript |
| Setup difficulty | easy | moderate | easy |
| Complexity | 2/5 | 4/5 | 2/5 |
| Audience | general | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Runs locally only, Unimarc, Tottus, and Lider require a residential internet connection, not a cloud server.
This project is an MCP server that lets you search products, compare prices, and build the best shopping list across Chilean supermarket chains directly from an AI assistant like Claude or ChatGPT. It covers the five biggest chains in the country: Jumbo, Santa Isabel, Unimarc, Tottus, and Lider. The README is explicit that it never runs as a hosted cloud service. It connects over a local stdio transport and runs entirely on your own machine, alongside your AI client. This is described as intentional rather than a limitation, for two reasons: several of these stores block traffic coming from cloud datacenters and only work from a normal home internet connection, and your logged in session, loyalty pricing, and shopping cart stay in your own browser instead of touching a central server, which avoids the legal risk of a service scraping other people's accounts. Each chain has different levels of support. Jumbo has the deepest integration, including search, member pricing, product detail, your frequent purchases, saved lists, and adding items to your actual cart. Santa Isabel shares much of that through the same backend. Unimarc offers search and club pricing. Tottus and Lider currently support search only. Results include normalized per unit pricing so you can compare different package sizes, plus any bundle deals like buy two for a set price. It installs with a single npx command added to your MCP client's configuration, requires Node.js 20 or newer, and can also be built from source for local development. It is released under the MIT license and reports 157 passing tests.
A local MCP server that lets Claude or ChatGPT search, compare prices, and build shopping lists across five Chilean supermarket chains.
Mainly TypeScript. The stack also includes TypeScript, Node.js, MCP.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly general.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.