Brazil Retail & Fuel Price Intelligence MCP Server
# Mestre Prático & NutriPreço — Brazil Retail & Fuel Price Intelligence MCP Server
[](https://mestrepratico.com.br/developers)
[](https://opensource.org/licenses/MIT)
Official sovereign **Model Context Protocol (MCP)** server providing real-time audited fuel prices (ANP) and grocery basket indices (SEFAZ NFC-e) across all **27 Brazilian states and 417+ cities**.
Built and maintained by **Holding Arthur Luis Vieira dos Santos** ([Mestre Prático](https://mestrepratico.com.br) & [NutriPreço](https://nutripreco.com.br)).
## 🌐 Live Remote MCP Endpoint (Zero-Install HTTP / Edge)
- **Endpoint URL:** `https://mestrepratico.com.br/mcp/v1`
- **Interactive Developer Portal:** [https://mestrepratico.com.br/developers](https://mestrepratico.com.br/developers)
- **Consumer Portals:** [Mestre Prático](https://mestrepratico.com.br) | [NutriPreço](https://nutripreco.com.br)
## 🔌 Quick Setup (Claude Desktop / Cursor / Windsurf)
Add this directly to your `claude_desktop_config.json` or MCP client settings:
```json
{
"mcpServers": {
"mestrepratico": {
"type": "http",
"url": "https://mestrepratico.com.br/mcp/v1"
}
}
}
```
## 🛠️ Available Tools
1. **`brazil_fuel_prices`**
- Queries official audited fuel prices (Regular Gasoline, Additive Gasoline, Ethanol, Diesel S10, CNG) from Brazil's National Petroleum Agency (ANP) across 4,750+ gas stations in all 27 states (`sp`, `rj`, `mg`, `ba`, `pr`, `rs`, `df`, etc.).
2. **`brazil_grocery_basket`**
- Queries and compares audited prices of Brazil's basic food basket (rice, beans, coffee, oil, milk, sugar, beef) sourced from electronic consumer invoices (NFC-e SEFAZ).
3. **`cost_of_living_brazil`**
- Returns consolidated regional cost-of-living metrics, purchasing power parity, and live BRL/USD comparisons for expats, digital nomads, and economic analysts.
## 📄 License
MIT License — Holding Arthur Luis Vieira dos Santos.
TDQS
Scored across 3 tools
Each tool targets a distinct dataset: fuel prices, grocery basket, and cost-of-living index. There is mild conceptual overlap between brazil_grocery_basket and cost_of_living_brazil (both touch on consumer costs), but the descriptions make the boundary reasonably clear.
Two tools follow a 'brazil_<noun>' prefix pattern (brazil_fuel_prices, brazil_grocery_basket), but cost_of_living_brazil puts the country at the end instead. Readable overall, but the pattern breaks in a small set where consistency is easy to achieve.
Three tools is thin for a data-intelligence server covering multiple datasets. Each tool earns its place, but the surface feels like a minimal MVP rather than a well-rounded set.
All three tools are read-only queries with no apparent supporting operations such as listing covered states, stations, time ranges, or comparing regions across datasets. The core query surface exists, but agents will hit dead ends for discovery and drill-down tasks.