Is Brazil Macro AI MCP server safe?

Findings (2)

• lowUnusually long tool description (over 2,000 characters)poison.long-description

  tool brazil_monetary_policy_divergence: …Assess divergence between Brazilian market-implied monetary policy, economist expectations, inflation breakevens and realized inflation surprises, using point-in-time public data with full provenance (method_id monetary_policy_divergence_v1). Consumes ONLY the already-homologated capability layer (market-vs-Focus meeting gaps, Focus Selic/IPCA 4-week revisions, the 5Y inflation breakeven and its 20-business-day change, and the latest eligible IPCA surprise) — never recomputes those engines and never fabricates a number a component doesn't support. Each of the 5 evidence components gets its own deterministic classification (strong_dovish..strong_ hawkish) with a versioned threshold set (threshold_version B4_THRESHOLDS_V1), quality-weighted by the underlying engine's own quality_status. `overall_signal` is a QUALITATIVE composite (strong_dovish/dovish/balanced/hawkish/strong_hawkish/ insufficient_evidence) — deliberately NOT a fabricated 0-100 score. `evidence_agreement` (0-1) tells you separately whether the components agree with each other, independent of the direction of the signal. IMPORTANT: `product_validation_status` is "internal_validated_external_ pending" until C0's external benchmark passes (see docs/C0_external_validation_protocol.md), then "validated" — several inputs (the market-implied Copom path, the real/breakeven curve) are themselves still individually pending external benchmark validation, never hidden here. This is macro intelligence, NOT an investment recommendation. Use when: assessing whether Brazilian market pricing, economist consensus, market-implied inflation and realized inflation data agree or diverge on the direction of monetary policy pressure. Do not use when: you need only one dimension — use compare_brazil_market_vs_focus, brazil_focus_revisions, brazil_inflation_breakeven, or brazil_macro_surprise directly. Args: as_of: optional YYYY-MM-DD date. Defaults to today. horizon_meetings: must be 4 in v1 (the PolicyGap weighting 0.40/0.30/0.20/0.10 is fixed for exactly 4 meetings). include_evidence: if true (default), include the full per-component evidence table (value, signal, quality_status, weights, validation status, source vintage). payment_token: required in staging ($0.25/call per pricing.yaml). …

• lowNo source repository listedmaint.no-repo