brazil-macro-ai

Brazil Macroeconomic and Financial Data AI Platform for AI agents.

CommunityDegradedNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Brazil Macroeconomic and Financial Data AI Platform for AI agents.

    How to connect

    How to connect brazil-macro-ai to Claude

    The server address to paste into Claude settings:

    https://api.brazilmacro.com/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect brazil-macro-ai to ChatGPT

    The server address to paste into ChatGPT settings:

    https://api.brazilmacro.com/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect brazil-macro-ai to Cursor

    The server address to paste into Cursor settings:

    https://api.brazilmacro.com/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (11)

    Raw names from tools/list. Only developers need these.

    get_brazil_selic_snapshotReturns Brazil's current policy rate (Selic target) plus realized short-term rates (Selic 252, CDI) and the last Copom decision. Use when: you need the current or historical Brazilian policy rate, or the most recent Copom decision, without needing forward-looking pricing. Do not use when: you need market expectations for FUTURE meetings — use get_brazil_copom_path or compare_brazil_market_vs_focus instead. Args: as_of: optional YYYY-MM-DD date for a historical snapshot (respects vintage — never uses data published after this date). Defaults to today. agent_id, session_id, discovery_source, payment_token: optional telemetry/access-policy fields (C1) — safe to omit; this capability is free and always returns 200 either way.
    get_brazil_copom_pathReturns market-implied Brazilian Selic expectations for upcoming Copom meetings, derived from B3 DI1 futures via a meeting-step bootstrap (method_id copom_path_di1_v1). Each entry gives the implied Selic level and the implied change in basis points for that specific meeting date — not rounded to 25bp increments. Use when: estimating expected BCB policy changes, the terminal rate, or cumulative easing/tightening priced by the market over the next 1-8 Copom meetings. Do not use when: you want economists' survey expectations instead of market pricing (use brazil_focus_revisions) or a direct comparison between the two (use compare_brazil_market_vs_focus). Limitations: requires liquid DI1 data for the as_of date's most recent trading day; DU counts use the validated B3 trading calendar (A6.1). Args: as_of: optional YYYY-MM-DD date. Defaults to today. meetings: number of upcoming Copom meetings to return (1-8, default 4). agent_id, session_id, discovery_source: optional C1 telemetry fields. payment_token: required in staging for this priced capability ($0.10/call per pricing.yaml) — omit to get the simulated payment_required response instead of a result.
    compare_brazil_market_vs_focusCompares the market-implied Copom path (DI1-derived) against the BCB Focus survey median, meeting-by-meeting (not just year-end), returning the gap in basis points per meeting and an overall dovish/hawkish classification (method_id market_vs_focus_meetings_v1). Use when: assessing whether Brazilian rates markets are pricing more or less monetary policy action than professional economists' consensus — useful for research agents, news agents, or risk agents monitoring Brazil-specific policy surprises. Do not use when: you only need one side of the comparison (use get_brazil_copom_path for market pricing alone, or Focus data directly for consensus alone). Args: as_of: optional YYYY-MM-DD date. Defaults to today. horizon: number of upcoming Copom meetings to compare (1-8, default 4). payment_token: required in staging ($0.15/call per pricing.yaml).
    brazil_focus_revisionsDetects whether Brazilian economists are revising inflation (IPCA), policy-rate (Selic), growth (PIB Total) or FX (Câmbio) expectations, and measures the speed and dispersion of those revisions — 1-week, 4-week and 13-week changes in the Focus survey median, plus a deterministic rising/falling/stable direction and accelerating/ decelerating/stable speed classification (method_id focus_revisions_v1). Built directly on Focus historical vintages — never recalculates a past date using data published after it. Use when: assessing sentiment shifts among professional economists for Brazil's main macro indicators, or whether a recent revision is speeding up or slowing down. Do not use when: you want market-implied pricing (use get_brazil_copom_path) or a market-vs-consensus comparison (use compare_brazil_market_vs_focus) — this tool is Focus-survey-only. Units are NOT always basis points — check the `unit` field in the response (bps for Selic/IPCA, percentage_points for PIB Total, BRL for Câmbio). Args: indicator: one of "Selic", "IPCA", "PIB Total", "Câmbio". reference_period: e.g. "2027" (the forecast year). Defaults to the current year. segment: "general" (all respondents) or "top5". Never mixed. as_of: optional YYYY-MM-DD date. Defaults to today. payment_token: required in staging ($0.05/call per pricing.yaml).
    brazil_yield_curveNominal Brazilian sovereign zero-coupon curve, bootstrapped from Tesouro Direto LTN (zero-coupon) and NTN-F (semi-annual coupon) offered-security quotes (method_id sovereign_zero_curve_bootstrap_v1). curve_scope = "tesouro_direto_offered_securities": this is NOT an institutional ANBIMA/Bloomberg ETTJ — it's derived from retail-offered public securities, published as open data (ODbL license). Tenors outside the curve's actual node coverage return status="unsupported", never extrapolated. Use when: you need Brazil's nominal risk-free curve shape or a specific nominal zero rate. Do not use when: you need the real (inflation-linked) curve (use brazil_real_curve) or breakeven inflation (use brazil_inflation_breakeven). Args: as_of: optional YYYY-MM-DD. Defaults to today. tenors: comma-separated subset of 1Y,2Y,3Y,5Y,7Y,10Y. Default: all. quote_side: "buy", "sell", or "mid" (default). payment_token: required in staging ($0.01/call per pricing.yaml).
    brazil_real_curveReal (IPCA-linked) Brazilian sovereign zero-coupon curve, bootstrapped from Tesouro Direto NTN-B Principal (zero-coupon) and NTN-B (semi-annual real coupon) offered-security quotes. Built entirely from the bonds' own quoted real yields — no Focus/IPCA projection is used anywhere in this engine. curve_scope = "tesouro_direto_offered_securities" (see brazil_yield_curve). Note: Tesouro currently offers no short-dated real zero-coupon bond, so this curve typically has NO coverage for 1Y/2Y tenors — check `status` per tenor. Use when: you need Brazil's real (inflation-protected) rate curve. Do not use when: you need the nominal curve (brazil_yield_curve) or breakeven inflation (brazil_inflation_breakeven). Args: as_of: optional YYYY-MM-DD. Defaults to today. tenors: comma-separated subset of 1Y,2Y,3Y,5Y,7Y,10Y. Default: all. quote_side: "buy", "sell", or "mid" (default). payment_token: required in staging ($0.03/call per pricing.yaml).
    brazil_inflation_breakevenMarket-implied Brazilian inflation breakeven — Fisher's EXACT identity ((1+nominal)/(1+real) - 1), never the linear approximation — computed only where the nominal and real curves both have support at the same tenor (method_id breakeven_fisher_v1). Returns `nominal_zero_rate_pct` and `real_zero_rate_pct` alongside the breakeven so the result is auditable. IMPORTANT: this is NOT "expected inflation" — it embeds risk premium, liquidity and convexity effects. The response field is deliberately named `market_implied_inflation_breakeven`. Use when: assessing what the market is pricing for future inflation, as distinct from Focus survey expectations (use brazil_focus_revisions with indicator="IPCA" for that). Do not use when: you need either curve alone (use brazil_yield_curve / brazil_real_curve). Args: as_of: optional YYYY-MM-DD. Defaults to today. tenors: comma-separated subset of 1Y,2Y,3Y,5Y,7Y,10Y. Default: all. quote_side: "buy", "sell", or "mid" (default). payment_token: required in staging ($0.03/call per pricing.yaml).
    brazil_macro_actualReturns a Brazilian macro headline actual (IPCA, IPCA-15, GDP, PIM-PF industrial production, PMC retail sales, PMS services volume, or PNAD Contínua unemployment) with full release-vintage provenance — built on a release/vintage layer that NEVER overwrites an original published number when a later revision arrives (method_id macro_actual_v1). Use when: you need the current headline reading for a Brazilian macro indicator, or (via `vintage`) what was known at a specific historical instant vs. what is currently the revised/correct value. Do not use when: you want the surprise vs. consensus (use brazil_macro_surprise, IPCA only) or the release schedule (use brazil_macro_calendar). Args: indicator: one of IPCA, IPCA15, GDP, PIM_PF, PMC, PMS, PNAD_UNEMPLOYMENT. reference_period: e.g. "2026-07" (monthly) or "2026-Q2" (GDP). as_of: YYYY-MM-DD, REQUIRED when vintage="as_known". vintage: "latest" (currently-correct value, default), "first" (original release, revision_number=0), or "as_known" (what was known publicly at `as_of`).
    brazil_macro_calendarOfficial IBGE release calendar for Brazilian macro indicators (IPCA, IPCA-15, GDP, PIM-PF, PMC, PMS, PNAD Contínua unemployment), with status transitions scheduled -> released -> corrected. Use when: you need to know when the next release of a Brazilian macro indicator is scheduled, or whether a given period has been released yet. Args: event: optional filter to one indicator (e.g. "IPCA"). Omit for all. upcoming_only: if true (default), only events not yet released. limit: max events returned (default 20).
    brazil_macro_surpriseCompare a Brazilian macroeconomic release with the latest public consensus that was available before the release, with full vintage and source provenance (method_id macro_surprise_v1). The consensus is ALWAYS the last Focus survey reading published strictly before the official release timestamp — never a reading published after it, and the actual is always the FIRST release, never a later revision. IMPORTANT: only computed for indicators with a methodologically valid, event-specific public consensus — currently IPCA only. GDP/PIM-PF/PMC/ PMS/PNAD_UNEMPLOYMENT raise an error rather than fabricate a consensus (use brazil_macro_actual for those — actual/momentum only, no surprise). Args: indicator: currently only "IPCA" is eligible. reference_period: e.g. "2026-07".
    brazil_monetary_policy_divergenceAssess 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. Arg