MCP Directory

agrobr-mcp

Give LLMs real-time Brazilian agricultural data — prices, crop estimates, climate and deforestation from public sources.

Unverified
stdio (local)
No auth
Python
View repo 25

Add to your client

Copy the config for your MCP client and paste it into its config file.

Install / run
pip install agrobr-mcp

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agrobr-mcp": {
      "command": "python",
      "args": [
        "-m",
        "agrobr_mcp"
      ]
    }
  }
}

Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf

Before you start

  • Python 3.11+
  • pip install agrobr-mcp (or Docker)

About agrobr-mcp

agrobr-mcp connects MCP clients (Claude Desktop, Cursor, Claude Code) to real-time Brazilian agricultural data. It is a thin wrapper over the agrobr Python library, which collects, parses, and caches data from 10+ public sources including CEPEA/ESALQ, CONAB, IBGE, INPE, B3, and NASA POWER. The server formats results as text and exposes 10 tools covering prices, production, climate, environment, and metadata. It runs over stdio and requires no authentication.

Tools & capabilities (10)

preco_diario

Daily spot prices for agricultural commodities (CEPEA/ESALQ).

futuros_b3

Daily settlement prices for agricultural futures on the B3 exchange.

estimativa_safra

Current crop season estimate by state (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).

clima

Climate data by state — temperature, precipitation, radiation (NASA POWER).

desmatamento

Deforestation rates and real-time alerts by biome (INPE).

listar_produtos

List valid products for each tool.

health_check

Check the status of all data sources.

When to use it

  • Ask in natural language for recent soybean or corn spot prices and B3 futures settlements.
  • Get current crop season estimates and historical production by Brazilian state.
  • Track weekly planting and harvest progress for a given crop.
  • Query climate data (temperature, precipitation, radiation) by state.
  • Monitor deforestation rates and real-time alerts by biome (e.g. the Amazon).

Security notes

No authentication or API keys required; all data is fetched from public Brazilian government and exchange sources. Data accuracy and availability depend entirely on those upstream public APIs.

agrobr-mcp FAQ

Does it require an API key?

No. All data comes from public Brazilian government and exchange sources, so no authentication or API keys are needed.

What is the relationship to the agrobr library?

agrobr-mcp is a thin MCP wrapper that handles tool exposure and text formatting. All data collection, parsing, and caching logic lives in the separate agrobr Python library.

How do I install it in Claude Code?

Run `claude mcp add agrobr python -- -m agrobr_mcp`. If the `-m` flag fails to parse, create a wrapper script (run.sh / run.bat) and add that instead.

Can I run it without installing Python locally?

Yes. Build the Docker image (`docker build -t agrobr-mcp .`) and configure your client to run `docker run --rm -i agrobr-mcp`.

#agriculture#brazil#commodities#climate#deforestation#finance#data#python

Alternatives to agrobr-mcp

Compare all alternatives →
Memory (Knowledge Graph)
AI, Data & Knowledge
74k

Official MCP server providing persistent, file-backed knowledge-graph memory across sessions.

Verified
stdio (local)
No auth
TypeScript
9 tools
Updated 5 months agoRepo
Sequential Thinking
AI, Data & Knowledge
62k

Structured step-by-step reasoning tool for breaking problems into revisable thought sequences.

Verified
stdio (local)
No auth
TypeScript
1 tool
Updated 6 months agoRepo
AWS Knowledge MCP
AI, Data & Knowledge
7.0k

Fully managed remote server for AWS docs, blogs, What's-New and Well-Architected guidance — no key.

Verified
HTTP (remote)
No auth
Hosted
6 tools
Updated 5 months agoRepo

Compare agrobr-mcp with:

vs Memory (Knowledge Graph)vs Sequential Thinkingvs AWS Knowledge MCPvs MCP Server Chart