FXMacroData is a remote MCP server that gives an AI agent 50 tools, among them announcement_changes, commodities, commodities_visual_artifact. It answers at https://fxmacrodata.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 22 October 2026, succeeded.
Macroeconomic and FX time-series data for AI agents: indicators, calendars, COT, forex, commodities.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
announcement_changes | Poll recently ingested macro announcement changes with a resumable cursor. This is the bounded MCP-safe companion to the release-event stream: use the returned next_cursor as since on a later call instead of holding an unbounded streaming t Inputs: currencies, indicators, since, limit, payload |
commodities | Get historical price series for supported commodity indicators using the exact slugs advertised by this schema. Requires an API key. Supported indicators: crude_oil_inventories, gold, natural_gas, natural_gas_storage, oil_brent, oil_wti, pl Inputs: indicator, symbol, start_date, end_date |
commodities_visual_artifact | Same payload as commodities, but packaged with MCP Apps chart metadata so compatible clients render an interactive commodity chart inline. Access: requires an FXMacroData API key; an anonymous call returns subscription_required with a subsc Inputs: indicator, start_date, end_date |
cot_data | Get weekly CFTC Commitment of Traders (COT) positioning data for a currency's FX futures contract on the CME. Use this when the user asks about speculator positioning, non-commercial longs vs shorts, hedge-fund FX positioning, or wants to g Inputs: currency, start_date, end_date |
cot_visual_artifact | Same payload as cot_data, but with MCP Apps chart metadata. By default it charts noncommercial net positioning; pass `metric` to chart another COT field. Access: requires an FXMacroData API key; an anonymous call returns subscription_requir Inputs: currency, start_date, end_date, metric |
data_catalogue | List every macroeconomic indicator FXMacroData publishes for a currency, with units, frequency, and coverage/freshness metadata. ALWAYS call this first when the user asks about a country's macro data — it returns the exact `indicator` slug Inputs: currency, include_coverage, include_capabilities, indicator |
event_impact_replay_task | Replay verified publication events against measured 1, 5 and 20-observation FX reference returns. Daily windows exclude the publication-day fixing; changes from previous actuals are not consensus surprises. Supports MCP Tasks for async exec Inputs: currency, indicator, base, quote, lookback_events, start_date |
event_predictions | Return stored forecasts, consensus-style predictions, central-bank projections, survey forecasts, IMF forecasts, nowcasts, or FXMacroData blended predictions for macro announcements. Use this with release_calendar and indicator_query when a Inputs: currency, indicator, prediction_type, prediction_source, start_date, end_date |
financial_prices | Read persisted official financial price observations: government yield curves, individual securities, overnight benchmarks and reference prices. Preserves issuer, instrument, maturity, curve type and source precision. Requires an API key; a Inputs: currency, source, start_date, end_date, measure, instrument_id |
forex | Get raw historical FX spot-rate rows for a currency pair (e.g. EUR/USD, USD/JPY). Prefer this tool when the user explicitly wants a plain-text table, raw rows, exact values, JSON-like data, or technical-indicator series (SMA, EMA, RSI, MACD Inputs: base, quote, start_date, end_date, indicators |
forex_visual_artifact | Same payload as forex, but packaged with MCP Apps chart metadata so compatible clients render an interactive spot-rate chart inline. Prefer this by default for FX pair time-series requests, especially for prompts like 'show me AUD/USD', 'te Inputs: base, quote, start_date, end_date, indicators |
fx_backtest_task | Run a spot-only FX backtest using historical policy-rate-differential and/or lagged momentum signals. Download complete histories, verify vintages and price coverage, and charge opening, rebalancing and closing costs. The carry signal does Inputs: base, quote, start_date, end_date, strategy, momentum_lookback |
fx_intraday_reference_rates | Return subscriber intraday official FX reference-rate observations for one pair. Call fx_reference_universe first to verify pair and source availability. Access: requires an FXMacroData API key; an anonymous call returns subscription_requir Inputs: base, quote, start_time, end_time |
fx_reference_sources | List public official FX reference-rate sources and their source policy before requesting a pair-specific intraday reference-rate series. Access: requires an FXMacroData API key; an anonymous call returns subscription_required with a subscri |
fx_reference_universe | List the public FX reference-rate pair universe, optionally filtered by currency or source id. Call this before requesting an intraday reference-rate series. Access: requires an FXMacroData API key; an anonymous call returns subscription_re Inputs: currency, source |
fx_trade_setup_task | Build a trader-oriented FX pair setup using spot context, macro differentials, upcoming catalyst risk, and optional COT positioning. Supports MCP Tasks for async execution when clients send task-augmented requests. Inputs: base, quote, horizon_events, include_cot |
indicator_intel_task | Build an intelligence pack for one indicator by combining chart-ready series data, derived analytics, and nearest release timing context. Supports MCP Tasks for async execution when clients send task-augmented requests. Access: USD is avail Inputs: currency, indicator, start_date, end_date |
indicator_query | Get a paginated historical time series of a single macroeconomic indicator for a currency, sourced directly from the official central bank or statistical agency. Use this for CPI/inflation, GDP, unemployment, policy rates, bond yields, payr Inputs: currency, indicator, start_date, end_date, limit, offset |
indicator_visual_artifact | Same payload as indicator_query, but also returns MCP Apps metadata so compatible clients (Claude Desktop, ChatGPT, Codex, etc.) render an interactive line chart instead of a JSON dump. Prefer this by default for indicator time-series reque Inputs: currency, indicator, start_date, end_date, limit, offset |
known_at_time_task | Return the slice of a macro series that would have been known at a specific timestamp, selecting verified value vintages before pagination. Supports MCP Tasks for async execution when clients send task-augmented requests. Access: USD is ava Inputs: currency, indicator, as_of, start_date, end_date, availability |
latest_announcements | Return the latest stored macroeconomic value for every available indicator in one currency. Use this for a compact current macro snapshot after data_catalogue has confirmed the currency coverage. Access: USD is available without an API key; Inputs: currency |
latest_commodities | Return the latest stored value for every available commodity indicator in one response. This subscriber tool is the batch counterpart to commodities. Access: requires an FXMacroData API key; an anonymous call returns subscription_required w |
macro_briefing_task | Build a compact macro briefing for a currency by combining catalogue, key macro series, release-calendar, prediction, news, risk-sentiment, COT, seasonality, and FX technical context. Supports MCP Tasks for async execution when clients send Inputs: currency |
macro_factor | Return a precomputed macro factor for one currency, with optional stored component scores and source references. Use this for a documented factor value, not as a substitute for inspecting its underlying macro releases. Access: USD is availa Inputs: currency, factor, start_date, end_date, include_components, include_sources |
macro_heatmap_task | Build a cross-currency macro heatmap from indicator time series and return a matrix with latest values, recent changes, and z-scores. Supports MCP Tasks for async execution when clients send task-augmented requests. Inputs: currencies, indicators, start_date, end_date |
macro_news | Return recent official central-bank news and press-release headlines for a currency. Use this when a report needs headline context for central-bank policy, inflation, employment, GDP, trade, fiscal, energy, or commodity narratives. The tool Inputs: currency, lookback_days, limit, offset |
macro_regime_classifier_task | Classify a currency's macro regime using policy rate, inflation, GDP, and unemployment context, with explicit assumptions and confidence notes. Supports MCP Tasks for async execution when clients send task-augmented requests. Access: USD is Inputs: currency, start_date, end_date |
macro_research_pack_task | Bundle catalogue, indicator history, next release timing, and optional FX pair context into one persistent-host-friendly research payload. Supports MCP Tasks for async execution when clients send task-augmented requests. Access: USD is avai Inputs: currency, indicator, base, quote, start_date, end_date |
macro_war_room_task | Build a multi-panel macro market cockpit that combines FX sessions, upcoming release queue, pair context, and generated risk alerts. Supports MCP Tasks for async execution when clients send task-augmented requests. Access: USD is available Inputs: base, quote, currency, indicator, start_date, end_date |
market_sessions | Tell the user which FX trading sessions are currently open (Sydney, Tokyo, London, New York) and when the next session opens/closes. Use this when the user asks 'is the market open?', 'when does London open?', or 'which sessions overlap rig Inputs: at |
mcp_auth_guide | Explain which authentication mode to use for FXMacroData MCP across major clients and platforms. Use this when the user asks whether to use OAuth, an API key, a bearer token, ChatGPT/OpenAI Apps, Claude/Anthropic, Microsoft/VS Code/Copilot- |
mcp_capabilities | Explain what the FXMacroData MCP server can do, which tools render MCP Apps, which tools return plain rows, what is public versus subscriber-only, and how to choose tools across ChatGPT, Claude, Cursor, Codex, and plain MCP clients. Use thi |
official_dataset_family | Get metadata-first official dataset payloads grouped by API endpoint type. Use endpoint_type to pick the API taxonomy group and dataset to choose the specific series family. Supported endpoint types: monetary_policy, fiscal_policy, internat Inputs: endpoint_type, dataset, currency, component |
pair_intel_task | Build an intelligence pack for an FX pair by combining policy-rate spread context, spot-rate context, and release-timing metadata. Supports MCP Tasks for async execution when clients send task-augmented requests. Access: requires an FXMacro Inputs: base, quote, start_date, end_date |
ping | Quick health check that confirms the FXMacroData API and MCP server are reachable. Use this only if other tools fail unexpectedly — it is not needed before normal calls. |
plot_visual_artifact | Build a generic MCP Apps chart from one or more FXMacroData endpoint families. Use this for arbitrary plot requests, multi-series charts, and actual-vs-consensus views that need to combine announcements with event_predictions. Supported ser Inputs: query, series, source, currency, indicator, base |
policy_rate_differential_visual_artifact | Build a two-series chart comparing base and quote policy-rate history to visualize the rate differential setup for an FX pair. Access: requires an FXMacroData API key; an anonymous call returns subscription_required with a subscribe link. Inputs: base, quote, start_date, end_date |
policy_scenario_modeler_task | Run a policy-rate spread what-if scenario for an FX pair and estimate directional spot impact using an explicit heuristic elasticity assumption. Supports MCP Tasks for async execution when clients send task-augmented requests. Access: requi Inputs: base, quote, shock_leg, shock_bps, policy_shock_bps, elasticity_per_100bps |
portfolio_risk_engine_task | Analyze a multi-position FX book for concentration, stress exposure, and event-driven catalyst risk. Supports MCP Tasks for async execution when clients send task-augmented requests. Inputs: positions_json, stress_shock_pct, horizon_events |
prediction_coverage | List which publishers produce pre-release forecasts for a currency's indicators, what class of forecast each one is (compiled consensus, forecaster survey, market implied, model nowcast, central-bank projection), whether any of them is a ge Inputs: currency |
press_releases, quant_scenario_lab_task, rate_curve, rate_differentials, release_calendar, release_calendar_visual_artifact, release_risk_score_task, risk_sentiment, seasonality, subscribe_for_mcp_access
Every block below points at https://fxmacrodata.com/mcp. Pick your client and copy.
claude mcp add --transport http fxmacrodata https://fxmacrodata.com/mcp
{
"mcpServers": {
"fxmacrodata": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://fxmacrodata.com/mcp"]
}
}
}{
"mcpServers": {
"fxmacrodata": {
"url": "https://fxmacrodata.com/mcp"
}
}
}{
"servers": {
"fxmacrodata": {
"type": "http",
"url": "https://fxmacrodata.com/mcp"
}
}
}{
"context_servers": {
"fxmacrodata": {
"url": "https://fxmacrodata.com/mcp"
}
}
}{
"mcpServers": {
"fxmacrodata": {
"serverUrl": "https://fxmacrodata.com/mcp"
}
}
}{
"mcpServers": {
"fxmacrodata": {
"url": "https://fxmacrodata.com/mcp"
}
}
}name: FXMacroData
version: 0.0.1
schema: v1
mcpServers:
- name: FXMacroData
type: streamable-http
url: https://fxmacrodata.com/mcp{
"mcpServers": {
"fxmacrodata": {
"httpUrl": "https://fxmacrodata.com/mcp"
}
}
}{
"mcpServers": {
"fxmacrodata": {
"type": "http",
"url": "https://fxmacrodata.com/mcp"
}
}
}{
"mcpServers": {
"fxmacrodata": {
"url": "https://fxmacrodata.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Ffxmacrodata.com%2Fmcp&type=streamable_http&id=fxmacrodata&name=FXMacroData
It answered our last check on 22 October 2026 in 134 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
50, as returned by the server's own tools/list on 14 September 2026: announcement_changes, commodities, commodities_visual_artifact, cot_data, cot_visual_artifact, data_catalogue, event_impact_replay_task, event_predictions, and 42 more.
It answered our last check on 22 October 2026 in 134 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://fxmacrodata.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.fxmacrodata. Endpoint host: fxmacrodata.com. ARD identifier: urn:air:io.github.fxmacrodata:mcp:fxmacrodata.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.