mcpSource-backedReview first Safety ✓ Privacy ✓

MCP-Brasil

Open source MCP server for querying Brazilian public data sources, including economic, legislative, transparency, judicial, electoral, environmental, health, education, public-safety, aviation, and infrastructure datasets.

by mcp-brasil contributors·added 2026-06-06·

Claude CodeClaude Desktop

HarnessClaude CodeClaude Desktop

Install

uvx --from mcp-brasil python -m mcp_brasil.server

Readiness

TrustReview first
Sourcesource-backed
Safety notesPresent
ReviewedYes

Documentation Source repository Registry JSON · LLM text

Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

MCP-Brasil can query many Brazilian public data sources, some of which cover courts, elections, health, public safety, government contracts, public spending, and regulated sectors.
The upstream acceptable-use policy prohibits doxing, stalking, unlawful electoral profiling, sensitive health-data misuse, unauthorized judicial data redistribution, re-identification, fake official claims, and other abusive uses.
Outputs should not be treated as official government records without checking the original source, because the MCP server is an independent open source project and LLM clients can misread or hallucinate.
Respect each upstream API's rate limits, license, attribution requirements, registration rules, and redistribution restrictions before batching or publishing results.
Large local datasets are opt-in and can download sizable public data caches; review disk usage, refresh behavior, and cache retention before enabling them.
Keep any optional DataJud, transparency, Meta, Anthropic, OAuth, or static bearer tokens scoped and separated from shared logs or test clients.

Privacy notes

Public records can still contain personal data or sensitive context, including judicial parties, health professionals, election candidates, public servants, suppliers, property records, campaign information, or location-linked records.
The upstream sources document highlights elevated risk for health, electoral, judicial, education, public-safety, and other datasets; operators remain responsible for LGPD compliance and source-specific terms.
Local DuckDB caches, terminal output, MCP client logs, chat transcripts, and exported analysis may retain query terms, public-record results, API keys, and derived datasets.
Do not disable PII masking or set `MCP_BRASIL_LGPD_ALLOW_PII` without a documented legal basis and a retention/deletion plan.
Attribute public data sources and preserve source context when sharing results with users or publishing downstream analysis.

Prerequisites

Python 3.10 or newer with `uvx` available.
Review of the upstream acceptable-use policy and source license notes before using outputs in commercial, journalistic, legal, medical, financial, electoral, or civic-decision workflows.
Optional API keys for data sources such as Portal da Transparencia, DataJud, or Meta Ad Library when those features are needed.
Optional local dataset cache configuration when enabling large DuckDB-backed datasets through `MCP_BRASIL_DATASETS`.
A plan for rate limiting, attribution, and human review when querying public agencies or redistributing analysis.

Schema details

Install type: cli
Troubleshooting: No

Source repository stats

Scope: Source repo

Collection metadata

Estimated setup: 15 minutes
Difficulty: advanced

Tool listing metadata

Disclosure: Community-maintained open source MCP server for Brazilian public data, published as the `mcp-brasil` Python package under the MIT license for code; upstream data sources have separate licenses and restrictions.

Full copyable content

{
  "mcpServers": {
    "mcp-brasil": {
      "command": "uvx",
      "args": ["--from", "mcp-brasil", "python", "-m", "mcp_brasil.server"],
      "env": {
        "TRANSPARENCIA_API_KEY": "OPTIONAL_TRANSPARENCIA_KEY",
        "DATAJUD_API_KEY": "OPTIONAL_DATAJUD_KEY",
        "META_ACCESS_TOKEN": "OPTIONAL_META_AD_LIBRARY_TOKEN",
        "MCP_BRASIL_DATASETS": "OPTIONAL_DATASET_IDS"
      }
    }
  }
}

About this resource

Content

MCP-Brasil connects Claude and other MCP clients to Brazilian public APIs and datasets. It is useful for supervised research and civic data workflows that need to inspect economic series, government transparency data, legislation, public spending, courts, elections, environmental data, health datasets, education statistics, public safety, aviation, infrastructure, and related public records.

Use it when an agent needs a source-aware way to search, plan, and execute Brazilian public-data queries while keeping attribution, acceptable-use limits, and privacy review in the workflow.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, PyPI metadata, license, package manifest, acceptable-use policy, data source notes, server entrypoint, and runtime settings for current setup, scope, and risk details.

Features

Query Brazilian public APIs across economic, legislative, transparency, judicial, electoral, environmental, health, education, security, aviation, energy, and infrastructure topics.
Search available features and tools before calling a specific data source.
Plan multi-step public-data queries with the planejar_consulta tool.
Execute batches of related calls through the server's batch-dispatch support.
Use optional API keys for data sources that require registration.
Enable large local DuckDB-backed datasets only when needed.
Run over stdio for local MCP clients or through FastMCP HTTP transport for hosted deployments.
Configure optional static bearer-token or OAuth authentication for HTTP deployments.

Installation

Install and run the published Python package with uvx:

{
  "mcpServers": {
    "mcp-brasil": {
      "command": "uvx",
      "args": ["--from", "mcp-brasil", "python", "-m", "mcp_brasil.server"],
      "env": {
        "TRANSPARENCIA_API_KEY": "OPTIONAL_TRANSPARENCIA_KEY",
        "DATAJUD_API_KEY": "OPTIONAL_DATAJUD_KEY",
        "META_ACCESS_TOKEN": "OPTIONAL_META_AD_LIBRARY_TOKEN",
        "MCP_BRASIL_DATASETS": "OPTIONAL_DATASET_IDS"
      }
    }
  }
}

Claude Code users can add the server with:

claude mcp add mcp-brasil -- uvx --from mcp-brasil python -m mcp_brasil.server

Most sources can be explored without optional API keys, but restricted sources such as transparency, judicial, or third-party ad-library data may need their own credentials and terms review.

Use Cases

Compare public economic indicators against legislative or budget activity.
Research public procurement, spending, contracts, suppliers, and sanctions.
Inspect legislative proposals, votes, representatives, and committees.
Explore environmental, health, education, or public-safety datasets with source attribution.
Combine multiple public sources into an auditable research plan.
Support civic-tech, journalism, policy research, and public-interest investigation workflows with human review.
Prototype internal data assistants for Brazilian public-data teams.

Safety and Privacy

MCP-Brasil is an access layer over public data, not an official source of truth. Review the upstream acceptable-use policy and source notes before using it for decisions, publication, compliance workflows, or redistribution.

Treat public-record results as potentially privacy-sensitive. Keep PII masking enabled, avoid re-identification, do not present AI-written summaries as official records, and verify high-impact answers against the original agency or data-source page.

Large local datasets can create durable DuckDB caches. Store them somewhere appropriate for the sensitivity of the queries, document who can access them, and delete caches when they are no longer needed.

#brazil#public-data#government#civic-tech#research

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.