Atlas / MCP servers / bruno-portfolio / Agrobr

AgrobrSAFE

mcp/bruno-portfolio/agrobr

MCP server for Brazilian agricultural data — connect LLMs to 10 public data sources via agrobr

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
10 10r · 0w · 0d
Transport
stdio
License
MIT
Stars
28
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

[](https://pypi.org/project/agrobr-mcp/) [](https://github.com/bruno-portfolio/agrobr-mcp/actions/workflows/tests.yml) [](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/)

MCP server that gives LLMs access to real-time Brazilian agricultural data — prices, crop estimates, climate, deforestation and more from 10 public sources from agrobr.

Install

pip install agrobr-mcp

Setup

Claude Desktop

Add to claude_desktop_config.json:

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

Cursor

Settings > MCP Servers > Add:

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

Claude Code

claude mcp add agrobr python -- -m agrobr_mcp
If the above fails due to -m flag parsing, create a wrapper script: Linux/macOS: echo 'python -m agrobr_mcp' > run.sh && chmod +x run.sh && claude mcp add agrobr ./run.sh Windows: echo python -m agrobr_mcp > run.bat && claude mcp add agrobr run.bat

Docker

docker build -t agrobr-mcp .
docker run --rm -i agrobr-mcp

Add to claude_desktop_config.json:

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

Tools

10 tools available out of the box:

Prices & Market

Read from source at commit 21acf12625a1OBSERVED · 2026-10-08
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code (pypi)
claude mcp add agrobr-mcp -- None agrobr-mcp==0.1.2
03

Exposed tools (10)

10 read · 0 write · 0 destructive.

ToolRiskDescription
balancoreadSupply and demand balance (stock, consumption, exports).
climareadRecent climate data by state (temperature, precipitation, radiation,
desmatamentoreadDeforestation rates and alerts by biome.
estimativa_safrareadCurrent crop season estimate by state (area, production, yield).
futuros_b3readDaily settlement prices for agricultural futures on B3 exchange.
health_checkreadCheck the status of agrobr data sources.
listar_produtosreadList valid products/parameters for each agrobr-mcp tool.
preco_diarioreadDaily spot prices for Brazilian agricultural commodities (CEPEA/ESALQ).
producao_anualreadHistorical annual crop production by state (IBGE PAM).
progresso_safrareadWeekly planting and harvesting progress by state.
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 21acf12625a1full audit observations/trust-audit/mcp-server/bruno-portfolio__agrobr.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-0821acf12625a1SAFEB89first audit
06

Questions

What is the Agrobr MCP server?

MCP server for Brazilian agricultural data — connect LLMs to 10 public data sources via agrobr

What tools does Agrobr expose?

10 in total: 10 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Agrobr safe to connect to an agent?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.

What credentials does Agrobr need?

No credential environment variables were found in its source, so it appears to need none.

How does Agrobr run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as agrobr-mcp.

How current is this page?

The grade is for one exact copy of the source (21acf12625a1), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement