mcp-brasil

mcp-brasil is a Python MCP server that exposes a large catalog of Brazilian public-data APIs (41 features, 326 tools) to AI agents via MCP. It includes meta-tools for smart discovery (BM25/code-mode), cross-referencing/planning across multiple APIs, and parallel batch execution. Some underlying APIs support optional API keys; the README claims most tools work without keys.

Evaluated Mar 30, 2026 (0d ago)
Repo ↗ DevTools mcp python ai-agents government-data brasil public-apis fastmcp tool-discovery batch-execution
⚙ Agent Friendliness
72
/ 100
Can an agent use this?
🔒 Security
60
/ 100
Is it safe for agents?
⚡ Reliability
39
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
82
Documentation
78
Error Messages
0
Auth Simplicity
90
Rate Limits
50

🔒 Security

TLS Enforcement
85
Auth Strength
60
Scope Granularity
20
Dep. Hygiene
65
Secret Handling
70

Security assessment is limited to README/manifest claims. The server is configured via environment variables for upstream API keys/tokens (reducing hard-coded secrets). No explicit guidance is provided about logging redaction, secure storage, or safe handling of tokens beyond env usage. Scope granularity is limited because keys are described as per-upstream API keys rather than fine-grained authorization scopes for the MCP server itself. TLS is not explicitly stated in the README, but HTTP client usage implies HTTPS for upstreams is likely; not guaranteed from provided data.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
50
Error Recovery
50
AF Security Reliability

Best When

You want an MCP-compatible integration to quickly access many Brazilian open/government APIs from an agent, with minimal setup and built-in tool discovery/planning.

Avoid When

You require strict idempotency guarantees, detailed error-code semantics, or you cannot tolerate inconsistent upstream API behaviors/parameter coverage.

Use Cases

  • Connect LLM/MCP clients to Brazilian government/public datasets (economic indicators, legislation, transparency, judiciary, elections, health, public safety, environment).
  • Multi-API research workflows (e.g., plan and cross-reference spending + votes + propositions).
  • Automated batch querying of many entities/time ranges via a single MCP call.
  • Discovery of relevant tools based on natural-language context to reduce tool-selection overhead.

Not For

  • Writing/transforming government data into authoritative outputs (the server is described as a proxy to upstream APIs, not an editor).
  • Environments requiring guaranteed data freshness/consistency beyond what upstream APIs provide.
  • Use cases needing formal SLAs, audited reliability guarantees, or strong contractual uptime.

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Environment variables for specific upstream APIs (e.g., TRANSPARENCIA_API_KEY, DATAJUD_API_KEY, META_ACCESS_TOKEN)
OAuth: No Scopes: No

README states keys are optional: without them, remaining APIs should function for 36 tools; 3 use keys (free registration). Auth is configuration via env vars/Claude/Desktop or .vscode JSON.

Pricing

Free tier: No
Requires CC: No

No product pricing described; it is an open-source server integrating third-party government APIs. Any costs would be indirect (compute and any upstream API charges, if applicable).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Large tool catalog (326 tools) may increase selection/search cost; use discovery mode/filters where supported.
  • Upstream APIs may have inconsistent parameter coverage and result variability (the README includes a disclaimer about partial coverage/unexpected results).
  • Some tools depend on optional upstream API keys; agents may see degraded coverage for those features without keys.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-brasil.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered