Mcp-Brasil/mcp-brasil
Infrastructure · tested 2026-09-24 · by the Hlido desk, not the vendor
In short: An ambitious open-source MCP server exposing 70 Brazilian public-data sources (533 tools) to AI agents — genuinely useful connective tissue, with unusually careful licensing and acceptable-use disclosures.
10 PASS · 0 FAIL of 10 public-surface claims
Quick answer
Mcp-Brasil/mcp-brasil scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-09-24). STEADY reflects a healthy, MIT-licensed repo with documented install, CI, releases, recent commits and real breadth, plus commendable licensing/AUP transparency. Pricing: Open source (free entry point documented).
mcp-brasil connects AI agents to Brazilian government and public data — economy, legislation, transparency, judiciary, elections, environment, health, education, public safety, fiscal, aviation — via a single MCP server advertising 533 tools, 131 resources, and 102 prompts across 70 features. The scope is large and the utility is real: getting reliable, structured access to dozens of Brazilian public APIs is exactly the kind of undifferentiated plumbing that makes agents useful in a national context, and 66 of the 70 sources need no API key. What stands out beyond scope is the project's honesty about it: a prominent disclaimer that it is NOT an official government service, MIT covering only the code (each data source keeps its own license), and an explicit Acceptable Use Policy for commercial, journalistic, or decisional use. That posture is exactly right for a tool intermediating sensitive public data. The caveats are inherent to breadth: 533 tools is a lot of surface to keep working as upstream APIs drift, and the review here is repo-health and public-surface, not a live exercise of each connector. Coverage and freshness will live or die on maintenance.
Why STEADY
STEADY reflects a healthy, MIT-licensed repo with documented install, CI, releases, recent commits and real breadth, plus commendable licensing/AUP transparency. Not higher because this is a public-surface + repo-health assessment (medium confidence) — Hlido did not exercise the 533 tools — and a connector aggregator of this size carries ongoing upstream-drift maintenance risk that only sustained activity can retire.
Public-surface checklist
- PASS Repo reachable (required) — GH API 200 for Mcp-Brasil/mcp-brasil
- PASS Readme present (required) — README length 20081
- PASS License present (required) — MIT
- PASS Install documented (required) — install/usage section found in README
- PASS Active 12mo (required) — last push 81d ago
- PASS Releases present — latest v0.14.0
- PASS Community traction — 1678 stars
- PASS Ci or tests — 4 workflow file(s)
- PASS Recent commit 90d — last push 81d ago
- PASS Agent consumable — MCP server markers in README
What we saw
1 screenshot captured by the Hlido engine during the reviewed run (run-5683724625766e9d-github-com). Our own captures — not vendor marketing material.
What it does well
- Broad, genuinely useful coverage: 70 Brazilian public-data sources through one MCP server
- 66 of 70 sources require no API key — low friction to start
- Exemplary transparency: clear "not an official government service" disclaimer, per-source licensing, published Acceptable Use Policy
- MIT-licensed code with documented install, CI, and release history
- FastMCP/Python stack that agents (Claude, GPT, Copilot) can consume directly
What it fails at
- 533 tools is a large surface to keep functioning as upstream government APIs change
- Data freshness and per-connector reliability depend on upstream sources Hlido cannot verify from the repo
- Narrow geographic scope — valuable for Brazil, irrelevant elsewhere
- No live, browsable demo of the connectors; assessment is repo + stated capability
- Per-source data licenses vary, so commercial use requires the buyer to check each one
Red flags
- Because it aggregates 70 external public APIs, availability and freshness are only as good as those upstream sources; the project cannot guarantee either, and this review did not exercise the connectors live.
Best for
- Developers building agents that need Brazilian government/public data (compliance, journalism, research, civic tech)
- Brazilian civic-tech, legal, and fintech teams wiring public data into LLM workflows
- Anyone who wants a single MCP endpoint instead of integrating dozens of public APIs by hand
- Research and transparency projects working with subnational fiscal, judicial, or electoral data
Not recommended for
- Teams outside Brazil with no need for Brazilian public data
- Use cases requiring an SLA or guaranteed data freshness (this depends on upstream public APIs)
- Commercial users unwilling to review each data source's individual license and the AUP
- Anyone expecting an official or government-endorsed data pipeline
Pricing & access
- ModelOpen source
- Free entry pointYes — a free tier or open-source edition is documented
Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-07-16.
Related agents
Agent relevance
MCP
Agentic-Commerce Readiness 44/100 · SURFACE-ONLY
Independent readiness for agent delegation & transaction. How it’s scored · check live
A FastMCP server exposing 533 tools / 131 resources / 102 prompts to any MCP-capable agent (Claude, GPT, Copilot). Built expressly for agent consumption; most sources are keyless.
Agent-friendly score: 8/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
Evidence
scorecard.json · transparency passport · registry · methodology
Embed this trust badge
Markdown
[](https://hlido.eu/check/?agent=mcp-brasil-mcp-brasil)HTML
<a href="https://hlido.eu/check/?agent=mcp-brasil-mcp-brasil"><img src="https://hlido.eu/badge/mcp-brasil-mcp-brasil.svg" alt="Hlido trust score"></a>