# bruno-portfolio/agrobr-mcp [Health: Active]

**Category:** 📊 Data Platforms  
**Repository:** https://github.com/bruno-portfolio/agrobr-mcp  
**GitHub Stars:** 29  
**Views:** 3  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/bruno-portfolio-agrobr-mcp

## Description
Brazilian agricultural data for LLMs — prices, crop estimates, climate, deforestation from 19 public sources via CEPEA, CONAB, IBGE, INPE and B3.

## Tools
Capabilities this server exposes over MCP:

- **preco_diario** — Daily spot prices for agricultural commodities (CEPEA/ESALQ)
- **futuros_b3** — Daily settlement prices for agricultural futures on B3 exchange (latest published session by default)
- **exportacao** — Agricultural exports summed by month, by product and state of origin (Comex Stat; ABIOVE fallback)
- **estimativa_safra** — Crop estimate by state, latest season with data by default (CONAB/IBGE)
- **producao_anual** — Historical annual production by state (IBGE PAM)
- **balanco** — Supply and demand balance — stock, consumption, exports (CONAB)
- **progresso_safra** — Weekly planting and harvesting progress by state (CONAB)
- **serie_historica_safra** — Historical crop series by season — area, production, yield; last 10 years by default (CONAB)
- **rebanho** — Livestock herds and animal products by state, latest published year by default (IBGE PPM)
- **clima** — Climate data by state — temperature, precipitation, radiation (NASA POWER)
- **desmatamento** — Deforestation polygons (PRODES for the previous calendar year, falling back one more year when empty) and alerts (DETER, last 15 days) by biome, with optional year and state filters, up to 2,000 records (INPE)
- **queimadas** — Fire hotspots of one day by municipality and biome, reference satellite (INPE)
- **listar_produtos** — List valid products for each tool
- **health_check** — Check status of all data sources

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `uvx` (confidence: high):

```json
"mcpServers": {
  "agrobr-mcp": {
    "command": "uvx",
    "args": ["agrobr-mcp"]
  }
}
```

## Documentation

## What bruno-portfolio/agrobr-mcp MCP server does

bruno-portfolio/agrobr-mcp MCP server gives language models access to Brazilian agricultural datasets through the Model Context Protocol. Its tools cover commodity markets, crop estimates and production, crop activity, climate measurements, and forest-loss information. Data is obtained from public services associated with CEPEA/ESALQ, B3, CONAB, IBGE, INPE, and NASA POWER.

The market tools return daily spot prices and B3 agricultural futures settlement prices. Production tools provide current season estimates by Brazilian state, historical annual production, supply-and-demand figures, and weekly planting or harvesting progress. Environmental tools provide climate values by state and deforestation rates or alerts by biome.

## How it works

An MCP client sends a natural-language request to the server and receives formatted tool output. The server itself is intentionally thin: the agrobr library performs data retrieval, parsing, and caching, while bruno-portfolio/agrobr-mcp exposes those functions through MCP.

The available tools are grouped into three practical areas:

- Markets: `preco_diario` and `futuros_b3`
- Production and crops: `estimativa_safra`, `producao_anual`, `balanco`, and `progresso_safra`
- Climate and environment: `clima` and `desmatamento`

`listar_produtos` helps identify valid products for the data tools. `health_check` reports the status of the connected data sources.

## Setup and configuration

Install the package with Python 3.11 or newer:

```bash
pip install agrobr-mcp
```

The server runs as a standard Python module over stdio:

```bash
python -m agrobr_mcp
```

For Claude Desktop, add a server entry whose command is `python` and whose argument is `-m agrobr_mcp`. Cursor uses the same command and argument pattern in its MCP server settings. Claude Code can register it with `claude mcp add agrobr python -- -m agrobr_mcp`; a wrapper script is available as a workaround if that command mishandles the `-m` argument.

A Docker image can also be built and run interactively, then referenced from an MCP client using `docker run --rm -i agrobr-mcp`.

## Tools and capabilities

Use `preco_diario` for daily CEPEA/ESALQ spot prices and `futuros_b3` for agricultural futures settlements on B3. Use `estimativa_safra` for current-season estimates by state and `producao_anual` for historical IBGE PAM production. `balanco` covers stocks, consumption, and exports, while `progresso_safra` reports weekly planting and harvest progress.

`clima` returns state-level temperature, precipitation, and radiation data from NASA POWER. `desmatamento` covers rates and real-time alerts by biome from INPE. The metadata and diagnostics tools are useful before querying: `listar_produtos` exposes accepted product names, and `health_check` checks source availability.

## Limitations and notes

bruno-portfolio/agrobr-mcp depends on external public data sources, so source availability and returned data may vary. The server does not implement the underlying agricultural data logic; that work belongs to the agrobr library. Product names should be checked with `listar_produtos` when a query requires a specific commodity. The repository provides development commands for running non-integration tests and Ruff checks, but no environment variables are documented as required for normal use.

_Full upstream README: https://allmcps.com/mcp/bruno-portfolio-agrobr-mcp/readme_