Agrobr MCP Server

Brazilian agricultural data for LLMs — prices, crops, climate, deforestation.

Local serverstdioPython

What is the Agrobr MCP server?

Brazilian agricultural data for LLMs — prices, crops, climate, deforestation. Exposed over MCP by the agrobr mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

agrobr-mcp is a thin wrapper. All data logic lives in the agrobr library.

Its toolset

Everything the assistant can do here goes through one of these:

  • preco_diario — Preço spot de commodities agrícolas (CEPEA/ESALQ)
  • futuros_b3 — Ajustes diários de futuros agrícolas na B3
  • estimativa_safra — Estimativa da safra corrente por UF (CONAB/IBGE)
  • producao_anual — Produção histórica por UF (IBGE PAM)
  • balanco — Balanço de oferta e demanda (CONAB)
  • progresso_safra — Progresso semanal de plantio e colheita (CONAB)
  • clima — Dados climáticos por UF (NASA POWER)
  • desmatamento — Taxa de desmatamento e alertas por bioma (INPE)
  • listar_produtos — Lista produtos válidos por tool
  • health_check — Status das fontes de dados
  • Cursor — The Cursor tool exposed by this server
  • Meta — The Meta tool exposed by this server

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at agrobr-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Agrobr's toolset — preco_diario, futuros_b3, estimativa_safra and 10 more — is a fair guide to whether it matches your workflow. It is maintained by bruno-portfolio; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Agrobr's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agrobr.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the agrobr mcp server does with a few real requests.

Available tools

ToolWhat it does
preco_diarioPreço spot de commodities agrícolas (CEPEA/ESALQ)
futuros_b3Ajustes diários de futuros agrícolas na B3
estimativa_safraEstimativa da safra corrente por UF (CONAB/IBGE)
producao_anualProdução histórica por UF (IBGE PAM)
balancoBalanço de oferta e demanda (CONAB)
progresso_safraProgresso semanal de plantio e colheita (CONAB)
climaDados climáticos por UF (NASA POWER)
desmatamentoTaxa de desmatamento e alertas por bioma (INPE)
listar_produtosLista produtos válidos por tool
health_checkStatus das fontes de dados
CursorThe Cursor tool exposed by this server.
MetaThe Meta tool exposed by this server.
LinksThe Links tool exposed by this server.

How to install the Agrobr MCP server

Add to `claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "agrobr": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "agrobr-mcp"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Agrobr to preco diario.
  • Use Agrobr to futuros b3.
  • Use Agrobr to estimativa safra.

Frequently asked questions

It connects Agrobr to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (preco_diario, futuros_b3, estimativa_safra, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agrobr directly.