Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

FXMacroData

REMOTE · FXMACRODATA.COM

Macroeconomic and FX time-series data for AI agents: indicators, calendars, COT, forex, commodities.

Available components

−1 this week 72 Trust /100

Last scanned (21 hours ago)

Scores higher than 57% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Finance and Payments

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability74
  • 94% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 13657 tokens (~210/item across 65 items; 52 tools + 13 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management41
  • Stability check failed: schema churn in the 30 days we've observed: 31 tool removals, 4 breaking changes, 0 auth/transport breaks, 27 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (48% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 52 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 54 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (14)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 −1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 41.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 42 to 43.

  • 16 Nov 26 −1
    • A breaking change shipped without a version bump: still 1.0.1 ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “catalogue_search” rewrote its description, which is the text the model reads security
    • Tool “macro_briefing_task” rewrote its description, which is the text the model reads security
    • Tool “macro_heatmap_task” rewrote its description, which is the text the model reads security
    • “catalogue_search” changed the type of “kind”: string → string|null ▼ functional
    • New resource “macro_monitor_view” functional
    • “catalogue_search” added an optional parameter “collection” cosmetic
    • “catalogue_search” added an optional parameter “data_type” cosmetic
    • “catalogue_search” added an optional parameter “dataset” cosmetic
    • “catalogue_search” added an optional parameter “frequency” cosmetic
    • “catalogue_search” added an optional parameter “page” cosmetic
    • “catalogue_search” added an optional parameter “page_size” cosmetic
    • “catalogue_search” added an optional parameter “q” cosmetic
    • “catalogue_search” added an optional parameter “sort” cosmetic
    • “catalogue_search” added an optional parameter “topic” cosmetic
    • “catalogue_search” added an optional parameter “view” cosmetic
    • “macro_briefing_task” added an optional parameter “checkpoint” cosmetic
    • “macro_briefing_task” added an optional parameter “currencies” cosmetic
    • “macro_briefing_task” added an optional parameter “since” cosmetic
    • “macro_briefing_task” added an optional parameter “timezone” cosmetic
    • “macro_heatmap_task” added an optional parameter “timezone” cosmetic
    • “catalogue_search” reworded the description of “country” cosmetic
    • “catalogue_search” reworded the description of “currency” cosmetic
    • “catalogue_search” reworded the description of “cursor” cosmetic
    • “catalogue_search” reworded the description of “kind” cosmetic
    • “catalogue_search” reworded the description of “limit” cosmetic
    • “catalogue_search” reworded the description of “publisher” cosmetic
    • “catalogue_search” reworded the description of “query” cosmetic
    • “macro_briefing_task” reworded the description of “base” cosmetic
    • “macro_briefing_task” reworded the description of “currency” cosmetic
    • “macro_briefing_task” reworded the description of “depth” cosmetic
    • “macro_briefing_task” reworded the description of “end_date” cosmetic
    • “macro_briefing_task” reworded the description of “indicator” cosmetic
    • “macro_briefing_task” reworded the description of “quote” cosmetic
    • “macro_briefing_task” reworded the description of “start_date” cosmetic
    • “macro_heatmap_task” reworded the description of “mode” cosmetic
    • Tool “catalogue_search” changed its title: Search the Connected Catalogue → Search the Data Catalogue cosmetic
  • 14 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “commodities” rewrote its description, which is the text the model reads security
    • Tool “research_paper_flatten” rewrote its description, which is the text the model reads security
    • “commodities” reworded the description of “indicator” cosmetic
    • “plot_visual_artifact” reworded the description of “indicator” cosmetic
  • 12 Nov 26 0
    • “indicator_query” added an optional parameter “date_basis” cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 42 to 45.

  • 10 Nov 26 −1
    • A breaking change shipped without a version bump: still 1.0.1 ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “cot_data” rewrote its description, which is the text the model reads security
    • Tool “macro_briefing_task” rewrote its description, which is the text the model reads security
    • Tool “research_paper_append_journal” rewrote its description, which is the text the model reads security
    • Tool “research_paper_archive” rewrote its description, which is the text the model reads security
    • Tool “research_paper_events” rewrote its description, which is the text the model reads security
    • Tool “research_paper_flatten” rewrote its description, which is the text the model reads security
    • Tool “research_paper_journal” rewrote its description, which is the text the model reads security
    • Tool “research_paper_list” rewrote its description, which is the text the model reads security
    • Tool “research_paper_pause” rewrote its description, which is the text the model reads security
    • Tool “research_paper_read” rewrote its description, which is the text the model reads security
    • Tool “research_paper_resume” rewrote its description, which is the text the model reads security
    • Tool “research_paper_revise_journal” rewrote its description, which is the text the model reads security
    • Tool “research_paper_start” rewrote its description, which is the text the model reads security
    • Tool “research_paper_start_version” rewrote its description, which is the text the model reads security
    • Tool “research_run_cancel” rewrote its description, which is the text the model reads security
    • Tool “research_run_list” rewrote its description, which is the text the model reads security
    • Tool “research_run_read” rewrote its description, which is the text the model reads security
    • Tool “research_run_reveal_holdout” rewrote its description, which is the text the model reads security
    • Tool “research_run_submit” rewrote its description, which is the text the model reads security
    • “macro_briefing_task” changed the type of “currency”: string → string|null ▼ functional
    • “indicator_query” added an optional parameter “base” cosmetic
    • “cot_data” reworded the description of “currency” cosmetic
    • “data_catalogue” reworded the description of “currency” cosmetic
    • “fx_backtest_task” reworded the description of “strategy” cosmetic
    • “indicator_query” reworded the description of “series_mode” cosmetic
    • “macro_briefing_task” reworded the description of “currency” cosmetic
    • “macro_briefing_task” reworded the description of “depth” cosmetic
    • “plot_visual_artifact” reworded the description of “currency” cosmetic
    • “rate_curve” reworded the description of “view” cosmetic
    • “rate_differentials” reworded the description of “rate_type” cosmetic
    • “release_calendar” reworded the description of “as_of” cosmetic
    • “release_calendar” reworded the description of “view” cosmetic
    • “macro_briefing_task” made “currency” optional cosmetic
  • 7 Nov 26 −3
    • Tool “indicator_intel_task” was removed ▼ security
    • Tool “macro_regime_classifier_task” was removed ▼ security
    • Tool “macro_research_pack_task” was removed ▼ security
    • Tool “macro_war_room_task” was removed ▼ security
    • Tool “pair_intel_task” was removed ▼ security
    • Tool “policy_scenario_modeler_task” was removed ▼ security
    • Tool “portfolio_risk_engine_task” was removed ▼ security
    • Tool “quant_scenario_lab_task” was removed ▼ security
    • Tool “release_risk_score_task” was removed ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “commodities” rewrote its description, which is the text the model reads security
    • Tool “cot_data” rewrote its description, which is the text the model reads security
    • Tool “event_impact_replay_task” rewrote its description, which is the text the model reads security
    • Tool “event_predictions” rewrote its description, which is the text the model reads security
    • Tool “forex” rewrote its description, which is the text the model reads security
    • Tool “fx_backtest_task” rewrote its description, which is the text the model reads security
    • Tool “fx_trade_setup_task” rewrote its description, which is the text the model reads security
    • Tool “geopolitical_event” rewrote its description, which is the text the model reads security
    • Tool “geopolitical_event_reaction” rewrote its description, which is the text the model reads security
    • Tool “geopolitical_event_revisions” rewrote its description, which is the text the model reads security
    • Tool “geopolitical_history” rewrote its description, which is the text the model reads security
    • Tool “geopolitical_sources” rewrote its description, which is the text the model reads security
    • Tool “indicator_query” rewrote its description, which is the text the model reads security
    • Tool “latest_announcements” rewrote its description, which is the text the model reads security
    • Tool “macro_briefing_task” rewrote its description, which is the text the model reads security
    • Tool “macro_heatmap_task” rewrote its description, which is the text the model reads security
    • Tool “macro_news” rewrote its description, which is the text the model reads security
    • Tool “official_datasets” rewrote its description, which is the text the model reads security
    • Tool “plot_visual_artifact” rewrote its description, which is the text the model reads security
    • Tool “press_releases” rewrote its description, which is the text the model reads security
    • Tool “rate_curve” rewrote its description, which is the text the model reads security
    • Tool “rate_differentials” rewrote its description, which is the text the model reads security
    • Tool “release_calendar” rewrote its description, which is the text the model reads security
    • Tool “release_calendar_visual_artifact” rewrote its description, which is the text the model reads security
    • Tool “research_paper_append_journal” rewrote its description, which is the text the model reads security
    • Tool “research_paper_archive” rewrote its description, which is the text the model reads security
    • Tool “research_paper_events” rewrote its description, which is the text the model reads security
    • Tool “research_paper_flatten” rewrote its description, which is the text the model reads security
    • Tool “research_paper_journal” rewrote its description, which is the text the model reads security
    • Tool “research_paper_list” rewrote its description, which is the text the model reads security
    • Tool “research_paper_pause” rewrote its description, which is the text the model reads security
    • Tool “research_paper_read” rewrote its description, which is the text the model reads security
    • Tool “research_paper_resume” rewrote its description, which is the text the model reads security
    • Tool “research_paper_revise_journal” rewrote its description, which is the text the model reads security
    • Tool “research_paper_start” rewrote its description, which is the text the model reads security
    • Tool “research_paper_start_version” rewrote its description, which is the text the model reads security
    • Tool “research_run_cancel” rewrote its description, which is the text the model reads security
    • Tool “research_run_list” rewrote its description, which is the text the model reads security
    • Tool “research_run_read” rewrote its description, which is the text the model reads security
    • Tool “research_run_reveal_holdout” rewrote its description, which is the text the model reads security
    • Tool “research_run_submit” rewrote its description, which is the text the model reads security
    • Tool “seasonality” rewrote its description, which is the text the model reads security
    • Prompt “commodity_fx_context” was removed ▼ functional
    • Prompt “cot_positioning_context” was removed ▼ functional
    • Prompt “data_quality_audit” was removed ▼ functional
    • Prompt “event_gated_backtest_brief” was removed ▼ functional
    • Prompt “known_at_time_backtest_check” was removed ▼ functional
    • Prompt “pair_risk_check” was removed ▼ functional
    • Prompt “portfolio_event_risk_scan” was removed ▼ functional
    • Prompt “post_release_trade_summary” was removed ▼ functional
    • Prompt “release_risk_ladder” was removed ▼ functional
    • Prompt “visualize_macro_series” was removed ▼ functional
    • Prompt “week_ahead_macro_plan” was removed ▼ functional
    • Tool coverage: 41% → 48% ▲ functional
    • Schema quality: good → excellent functional
    • Server version: 2.3.0 → 1.0.1 functional
    • “fx_trade_setup_task” added an optional parameter “end_date” cosmetic
    • “fx_trade_setup_task” added an optional parameter “start_date” cosmetic
    • “fx_trade_setup_task” added an optional parameter “view” cosmetic
    • “macro_briefing_task” added an optional parameter “base” cosmetic
    • “macro_briefing_task” added an optional parameter “depth” cosmetic
    • “macro_briefing_task” added an optional parameter “end_date” cosmetic
    • “macro_briefing_task” added an optional parameter “indicator” cosmetic
    • “macro_briefing_task” added an optional parameter “quote” cosmetic
    • “macro_briefing_task” added an optional parameter “start_date” cosmetic
    • “macro_heatmap_task” added an optional parameter “base” cosmetic
    • “macro_heatmap_task” added an optional parameter “currency” cosmetic
    • “macro_heatmap_task” added an optional parameter “indicator” cosmetic
    • “macro_heatmap_task” added an optional parameter “mode” cosmetic
    • “macro_heatmap_task” added an optional parameter “quote” cosmetic
    • “fx_trade_setup_task” reworded the description of “horizon_events” cosmetic
    • “geopolitical_history” reworded the description of “date_basis” cosmetic
    • “indicator_query” reworded the description of “availability” cosmetic
    • “indicator_query” reworded the description of “value_mode” cosmetic
    • “release_calendar” reworded the description of “event_kind” cosmetic
    • Tool “event_impact_replay_task” changed its title: Event Impact Replay Task → Event Impact Replay cosmetic
    • Tool “fx_backtest_task” changed its title: FX Backtest Task → FX Backtest cosmetic
    • Tool “fx_trade_setup_task” changed its title: FX Trade Setup Task → FX Trade Setup Analysis cosmetic
    • Tool “macro_briefing_task” changed its title: Macro Briefing Task → Macro Briefing cosmetic
    • Tool “macro_heatmap_task” changed its title: Macro Heatmap Task → Macro Heatmap cosmetic
    • Tool “plot_visual_artifact” changed its title: Plot Visual Artifact → Plot Chart cosmetic
    • Tool “release_calendar_visual_artifact” changed its title: Release Calendar Visual Artifact → Release Calendar View cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://fxmacrodata.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=fxmacrodata.com CN=YE1,O=Let's Encrypt,C=US 20 Nov 2026 18 Feb 2027 ECDSA 256 ECDSA-SHA384 5af0d969b795341d63440ca25fc75d9f7ed
SANs: *.fxmacrodata.com, fxmacrodata.com
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of fxmacrodata.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
fxmacrodata.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
content-security-policy default-src 'self' https: data: blob:; script-src 'self' 'unsafe-inline' https://cdnjs.cloudflare.com https://cdn.jsdelivr.net https://cdn.plot.ly https://cdn.ampproject.org https://appsforoffice.microsoft.com https://www.googletagmanager.com https://apis.google.com https://www.gstatic.com https://assets.endorsely.com https://googleads.g.doubleclick.net https://static.cloudflareinsights.com; style-src 'self' 'unsafe-inline' https:; img-src 'self' data: blob: https:; font-src 'self' data: https:; connect-src 'self' https: wss:; frame-src 'self' https:; object-src 'none'; base-uri 'self'; frame-ancestors 'self'; upgrade-insecure-requests; trusted-types default goog#html gapi#gapi 'allow-duplicates'
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://fxmacrodata.com/mcp Verified 200
http (plaintext) http://fxmacrodata.com/mcp HTTPS enforced 301 https://fxmacrodata.com/mcp
MCP tools · 52 exposed · ~11,117 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
catalogue_related ~184

Follow evidence-linked catalogue relationships from a node ID returned by catalogue_search. Depth is one or two, limit is at most fifty; use the returned cursor for more results. Paths explain recorded metadata relationships, not causality or series equivalence. Retrieval tools enforce their existing data access rules. Access: public metadata relationships, no API key required.

NameTypeReqDescription
cursorstring|null–Opaque next_cursor from the preceding result with unchanged filters; omit for page one.
depthinteger–Relationship traversal depth: 1 (direct) or 2 (one additional hop).
limitinteger–Maximum results per page, 1-50.
node_idstringyesExact opaque node ID from a catalogue result; do not construct an ID.
relationshipstring|null–Optional edge type: published_by, about_country, cites_source or related_series.
NameTypeReqDescription
resultobjectyes–

No examples provided.

catalogue_search ~222

Search website dataset metadata or graph relationships. Access: public catalogue metadata, no API key required.

NameTypeReqDescription
collectionstring–Parent collection ID.
countrystring|null–Graph country code.
currencystring|null–Currency facet; either FX leg.
cursorstring|null–Graph cursor from results.
data_typestring–Data type facet.
datasetstring–Exact result ID.
frequencystring–Frequency facet.
kindstring|null–Kind from facets; graph uses lowercase (default series).
limitinteger–Graph page size.
pageinteger–One-based result page.
page_sizeinteger–Page size, 1-50.
publisherstring|null–Publisher facet or graph ID.
qstring|null–Keyword search.
querystring–Search text alias.
sortstring–Result sort order.
topicstring–Topic from facets.
viewstring–Website datasets or graph.
NameTypeReqDescription
resultobjectyes–

No examples provided.

commodities ~268

Get historical price series for supported commodity indicators using the exact slugs advertised by this schema. Supported indicators: crude_oil_inventories, crude_oil_stocks, distillate_inventories, distillate_stocks, gasoline_inventories, gasoline_stocks, gold, natural_gas, natural_gas_storage, natural_gas_storage_level, oil_brent, oil_wti, platinum, silver. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
end_datestring|null–Inclusive upper bound, YYYY-MM-DD.
indicatorstring|null–Commodity indicator slug. Supported: crude_oil_inventories, crude_oil_stocks, distillate_inventories, distillate_stocks, gasoline_inventories, gasoline_stocks, gold, natural_gas, natural_gas_storage,…
latestboolean–Set true for one snapshot of the latest stored value of every commodity indicator; `indicator` is then not needed.
start_datestring|null–Inclusive lower bound, YYYY-MM-DD.
symbolstring|null–Backward-compatible alias for `indicator`, which supersedes it in new calls.
NameTypeReqDescription
resultobjectyes–

No examples provided.

cot_data ~412

Get weekly CFTC Commitment of Traders (COT) positioning data for a currency's FX futures contract on the CME, covering speculator positioning, non-commercial longs vs shorts, hedge-fund FX positioning, and sentiment extremes. Returns weekly snapshots with long/short open interest by trader category. Updated every Friday at 15:30 ET reflecting the Tuesday cutoff. USD (the USD Index contract) is available without an API key for the most recent 90 days on a 15-minute release delay; every other currency and the full history need an API key. Supported currencies: AUD, CAD, CHF, EUR, GBP, JPY, MXN, NZD, USD, XAU. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
currencystring|null–3-letter ISO currency code for the FX futures contract (case-insensitive). Supported: AUD, CAD, CHF, EUR, GBP, JPY, MXN, NZD, USD, XAU.
end_datestring|null–Inclusive upper bound, YYYY-MM-DD.
instrumentstring|null–Any CFTC contract by instrument id (rates, equity, energy, metals and micro contracts) instead of a currency. Use `list` to see the supported instrument/report combinations.
limit––Rows per page for instrument reads (1-100).
offset––Row offset for instrument reads.
reportstring|null–CFTC report type. Omit for the Legacy futures-only report (commercial / non-commercial / non-reportable). One of: legacy_futures, legacy_combined, tff_futures, tff_combined, disaggregated_futures. TF…
start_datestring|null–Inclusive lower bound, YYYY-MM-DD.
NameTypeReqDescription
resultobjectyes–

No examples provided.

data_catalogue ~466

List every macroeconomic indicator FXMacroData publishes for a currency, with units, frequency, and coverage/freshness metadata. Returns the exact `indicator` slug strings used across FXMacroData indicator, calendar, and prediction endpoints. Rows whose `coverage` is stale, partial, or unavailable are not suitable for real-time carry or inflation analysis. Other views, all free: `forecasts` shows which publishers forecast which indicators and how far each archive runs (no forecast values); `fx_sources` lists official FX reference-rate publishers; `fx_universe` lists the pairs each one covers; `sources` returns a persisted source definition by its metadata `sha256`. Access: all currencies keyless.

NameTypeReqDescription
currencystring|null–3-letter ISO currency code (case-insensitive). Required for the indicators and sources views; optional filter for the others. Supported: AUD, BRL, CAD, CHF, CNH, CNY, CZK, DKK, EUR, GBP, HUF, IDR, IL…
include_capabilitiesboolean–Include machine-readable indicator capabilities when the API supports them, such as supported transformations, history availability, and release-calendar linkage.
include_coverageboolean–Include coverage/freshness rows with latest_available_date, coverage_quality, has_recent_data, and recent_observation_count. These rows show whether an indicator series is current enough for analysis.
indicatorstring|null–Optional indicator slug that narrows the result to that one catalogue entry and its coverage row, for example `core_inflation`. Useful when the candidate series is already known; omit it to list ever…
sha256string|null–sources only: the metadata SHA256 from a catalogue row.
sourcestring|null–fx_universe only: official source id filter.
viewstring–indicators (default): the indicator catalogue. forecasts: forecast coverage by publisher. fx_sources / fx_universe: official FX reference-rate publishers and the pairs they cover. sources: one persis…
NameTypeReqDescription
resultobjectyes–

No examples provided.

event_impact_replay_task ~266

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. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
basestring|null–FX base currency for market context, 3-letter ISO code (case-insensitive). Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
currencystringyesCurrency for macro event series, 3-letter ISO code (case-insensitive). Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
end_datestring|null–Optional inclusive upper bound, YYYY-MM-DD.
indicatorstringyesIndicator slug for event replay. Supported examples: catalogue indicator slug, e.g. inflation or policy_rate.
lookback_eventsinteger|null–Maximum number of recent events to include in replay.
quotestring|null–FX quote currency for market context, 3-letter ISO code (case-insensitive). Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
start_datestring|null–Optional inclusive lower bound, YYYY-MM-DD.

No output schema declared.

No examples provided.

event_predictions ~621

Return stored forecasts, consensus-style predictions, central-bank projections, survey forecasts, IMF forecasts, nowcasts, or FXMacroData blended predictions for macro announcements, for actual-vs-consensus, prior-vs-forecast, or event-surprise context. Rows are keyed by announcement_id/date/indicator and include prediction source metadata. Supported currencies: lowercase 3-letter catalogue currency, e.g. usd or eur. The `indicator` parameter lists the accepted indicator slugs. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
annualizationstring|null–Annualization selector, matching the announcement series.
as_ofstring|null–Historical publication cutoff with explicit timezone, or YYYY-MM-DD at UTC midnight. Later forecasts are excluded.
basisstring|null–Real or nominal selector, matching the announcement series.
before_datestring|null–Exclusive period-date cursor for event-linked groups; use the prior response's next_cursor.
currencystringyes3-letter ISO currency code (case-insensitive). Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
end_datestring|null–Optional inclusive upper bound by reference-period date, YYYY-MM-DD.
event_compatible_onlyboolean–Restrict event-linked data to verified matching target periods, units and economic concepts. Native official_forecasts remain a separate section.
frequencystring|null–Returned change basis selector, matching the announcement series.
indicatorstringyesRequired indicator slug. Currency-wide prediction reads are not supported. Supported: catalogue indicator slug, e.g. inflation or policy_rate.
limitinteger–Maximum prediction groups to return. Defaults to 20; maximum 100.
official_limitinteger–Maximum native-period official forecasts; 0 omits this section. Inspect official_forecasts_truncated.
offsetinteger–Zero-based prediction-group offset.
page––One-based page number. When supplied, overrides offset.
period_aggregationstring|null–Period aggregation selector, matching the announcement series.
pre_release_onlyboolean–Require event-linked forecasts to have been generated before the announcement.
prediction_classstring|null–Forecast production class: compiled_consensus, forecaster_survey, expectations_survey, market_implied, model_nowcast, central_bank_projection, institutional_projection or fxmacrodata.
prediction_sourcestring|null–Optional source slug filter, for example ecb_spf or philly_fed_spf.
prediction_typestring|null–Optional legacy forecast-type filter, kept for existing clients. Superseded by prediction_class: compiled_consensus, forecaster_survey, expectations_survey, market_implied, model_nowcast, central_ban…
seasonalitystring|null–Seasonal adjustment selector, matching the announcement series.
start_datestring|null–Optional inclusive lower bound by reference-period date, YYYY-MM-DD.
NameTypeReqDescription
resultobjectyes–

No examples provided.

forex ~412

Get raw historical FX spot-rate rows for a currency pair (e.g. EUR/USD) as a plain-text table, raw rows, exact values, or JSON-like data, without chart metadata. Daily official central-bank reference rates with multi-year history. Optional technical-indicator series (SMA, EMA, RSI, MACD, Bollinger Bands, etc.) are selected by comma-separated slugs in indicators; interval selects daily or intraday. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
basestringyesBase currency, 3-letter ISO code (case-insensitive). Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
end_datestring|null–Inclusive upper bound, YYYY-MM-DD. Defaults to today.
end_timestring|null–intraday only: inclusive RFC 3339 upper bound.
indicatorsstring|null–Comma-separated technical-indicator slugs to attach to each row. Supported: adx_14, atr_14, bollinger_bands, cci_20, donchian_20, ema_12, ema_20, ema_200, ema_26, ema_50, macd, macd_histogram, macd_s…
intervalstring–daily (default): spot history. intraday: timestamped official intraday reference-rate fixings for the pair, bounded by start_time and end_time.
quotestringyesQuote currency, 3-letter ISO code (case-insensitive). Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
start_datestring|null–Inclusive lower bound, YYYY-MM-DD. Defaults to ~5 years ago.
start_timestring|null–intraday only: inclusive RFC 3339 lower bound.
NameTypeReqDescription
resultobjectyes–

No examples provided.

fx_backtest_task ~307

Run a spot-only FX backtest using historical policy-rate-differential and/or lagged momentum signals. Downloads complete histories, verifies vintages and price coverage, and charges opening, rebalancing and closing costs. The carry signal does not include funding income or broker rollover. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
basestringyesBase currency, 3-letter ISO code. Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
end_datestring|null–Inclusive upper bound, YYYY-MM-DD.
event_gatedboolean|null–When true, allow positions only after verified historical policy publications for either currency. This does not use future calendars or trade before a release.
event_window_daysinteger|null–Additional calendar days after the first UTC decision following publication; 0 permits that first day only.
initial_capitalnumber|null–Starting capital for equity-curve calculations.
momentum_lookbackinteger|null–Momentum lookback in observations for the momentum signal.
quotestringyesQuote currency, 3-letter ISO code. Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
start_datestring|null–Inclusive lower bound, YYYY-MM-DD.
strategystring|null–Signal mode.
transaction_cost_bpsnumber|null–Per-side transaction cost in basis points applied on position changes.

No output schema declared.

No examples provided.

fx_trade_setup_task ~268

Build a trader-oriented FX pair setup using spot context, macro differentials, upcoming catalyst risk, and optional COT positioning. Set view for pair context only or a ranked event-risk score. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
basestringyesBase currency, 3-letter ISO code. Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
end_datestring|null–view='pair_intel' only: inclusive upper bound, YYYY-MM-DD.
horizon_eventsinteger|null–Maximum upcoming catalysts per leg to rank. Defaults to 4, or 6 for view='release_risk'.
include_cotboolean|null–When true, attempt to include COT positioning context for both legs.
quotestringyesQuote currency, 3-letter ISO code. Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
start_datestring|null–view='pair_intel' only: inclusive lower bound, YYYY-MM-DD.
viewstring–setup (default) builds the full trade setup. pair_intel returns spot, carry and policy-differential context. release_risk ranks upcoming event risk for the pair.

No output schema declared.

No examples provided.

geopolitical_event ~112

Full stored record of one official-source geopolitical event, by event_id, with separate incident, publication and capture dates; as_of returns it as known at a past cutoff. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
as_ofstring|null–Knowledge cutoff with timezone, e.g. 2024-06-30T23:59:59Z; omit for latest.
event_idstringyesEvent ID from history results: exactly 64 lowercase hexadecimal characters.
NameTypeReqDescription
resultobjectyes–

No examples provided.

geopolitical_event_reaction ~130

Precomputed FX reference-price moves for one currency pair around one geopolitical event, by event_id. Context only: not causation or a trading signal. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
as_ofstring|null–Knowledge cutoff with timezone, e.g. 2024-06-30T23:59:59Z; omit for latest.
event_idstringyesEvent ID from history results: exactly 64 lowercase hexadecimal characters.
pairstring–Uppercase BASE/QUOTE currency pair, e.g. EUR/USD.
NameTypeReqDescription
resultobjectyes–

No examples provided.

geopolitical_event_revisions ~151

Every stored revision of one geopolitical event's source record, by event_id, showing how the publisher changed it over time; as_of limits it to what was known at a past cutoff. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
as_ofstring|null–Knowledge cutoff with timezone, e.g. 2024-06-30T23:59:59Z; omit for latest.
event_idstringyesEvent ID from history results: exactly 64 lowercase hexadecimal characters.
limitinteger–Maximum rows per page, 1-100.
offsetinteger–Zero-based row offset; 0 starts the first page.
NameTypeReqDescription
resultobjectyes–

No examples provided.

geopolitical_history ~361

Search stored official sanctions (OFAC) and maritime-security (UKMTO) records by source, country, date or text. Each row carries the event_id the other geopolitical tools take and its revision history. Paged with limit and offset. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
after_revisioninteger–Return revisions newer than this non-negative watermark; 0 disables the incremental filter.
as_ofstring|null–Knowledge cutoff with timezone, e.g. 2024-06-30T23:59:59Z; omit for latest.
countrystring|null–Uppercase ISO 3166-1 alpha-2 country link, e.g. US; omit for all countries.
date_basisstring–Which date start_date and end_date filter on.
end_datestring|null–Inclusive upper date bound, YYYY-MM-DD, e.g. 2024-12-31.
include_undatedboolean–Retain undated records when start_date or end_date filters are supplied.
limitinteger–Maximum rows per page, 1-100.
offsetinteger–Zero-based row offset; 0 starts the first page.
searchstring|null–Text filter, at most 160 characters, e.g. sanctions.
source_idstring|null–Official source ID from source coverage, e.g. ofac_actions; omit for all sources.
start_datestring|null–Inclusive lower date bound, YYYY-MM-DD, e.g. 2024-01-01.
subtypestring|null–Exact source-record subtype from history results; omit for all subtypes.
NameTypeReqDescription
resultobjectyes–

No examples provided.

geopolitical_sources ~47

Lists the official geopolitical sources held: source_id values, record counts, collection outcomes and coverage limits. Takes no arguments. Access: API key required, else returns subscription_required with a subscribe link.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultobjectyes–

No examples provided.

indicator_query ~734

Returns one currency/indicator's persisted official-producer history using catalogue identifiers. Rows contain `date` (reference period), numeric `val` and separate publication evidence; no chart metadata. `as_of` selects historically eligible values; current values may include revisions. Newest-first pagination: default 100 rows with `start_date`, otherwise 20; `limit` maximum 100. When `pagination.has_more`, `partial_page.next_call` contains next-page arguments; `partial_page.pages_remaining` counts remaining pages. Official-only by default; prohibited private aggregator rows are always removed. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
as_ofstring|null–Historical decision cutoff with explicit timezone, or YYYY-MM-DD at UTC midnight; verifies vintages before returning rows.
availabilitystring–Replay clock, used with as_of.
basestring|null–Index or price base, such as 2024. `supported_options.base` lists the values for this indicator; each base is a separate official series and bases are never joined.
currencystring|null–3-letter ISO currency code (case-insensitive). Optional if `slug` is provided as a `"usd:cpi"`-style compound. Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
dataset_versionstring|null–Optional content version; use the first page's version on subsequent pages to reject changed data.
date_basisstring|null–Observation-date convention. Use only a value listed by this indicator's supported_options.date_basis; each convention reads a separate stored series without re-dating observations.
end_datestring|null–Inclusive upper bound, YYYY-MM-DD.
factorstring|null–Instead of an indicator, return a precomputed macro factor score for `currency`, for example monetary_stance.
include_componentsboolean|null–factor only: include the stored component scores.
include_sourcesboolean|null–factor only: include source endpoint references.
indicatorstring|null–Indicator slug for the given currency. Optional if `slug` is provided as a `"usd:cpi"`-style compound. Supported: catalogue indicator slug, e.g. inflation or policy_rate.
limit––Rows per page, newest first, maximum 100. Unset means 100 when `start_date` is set, otherwise 20.
official_onlyboolean–When true, return only official-source rows and remove explicit fallback observations. Prohibited private aggregator rows are always removed.
offsetinteger–Zero-based row offset after most-recent-first ordering. Take it from `partial_page.next_call`.
page––One-based page number. When supplied, the REST endpoint derives offset as `(page - 1) * limit`.
revisionsstring|null–Revision view: latest, first, final or all. Historical replay uses latest among vintages eligible at as_of.
series_modestring|null–Series mode. Historical replay defaults to raw.
slugstring|null–Optional compound `"<currency>:<indicator>"` slug (e.g. `"usd:cpi"`, `"jpy:policy_rate"`). Many small / open tool-calling models concatenate the two parts anyway. When supplied, overrides `currency`…
start_datestring|null–Inclusive lower bound, YYYY-MM-DD.
value_modestring|null–Value mode. Historical replay defaults to unchanged source values and requires raw series mode.
NameTypeReqDescription
resultobjectyes–

No examples provided.

latest_announcements ~248

Return the latest stored macroeconomic value for every available indicator in one currency, as a compact current macro snapshot. An unverified announcement_datetime has unproven origin; it is neither a verified scheduled time nor observed actual publication. Report absent schedule, publication and ingestion evidence as unknown, and latency as not measured. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
currenciesstring|null–changes only: comma-separated codes, `g10` or `all`.
currencystring|null–3-letter ISO currency code (case-insensitive). Required for the latest view.
indicatorsstring|null–changes only: comma-separated indicator slugs.
limit––changes only: page size, default 100.
payloadstring|null–changes only: compact (default) or full rows.
sincestring|null–changes only: previous next_cursor, ISO 8601 time or epoch seconds.
viewstring–latest (default): newest value per indicator for `currency`. changes: a resumable feed of newly ingested announcements across currencies; pass the returned next_cursor back as `since`.
NameTypeReqDescription
resultobjectyes–

No examples provided.

macro_briefing_task ~275

Macro research or checkpointed morning changes across supported economic series. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
basestring|null–research_pack only: pair base currency.
checkpoint––morning: next_checkpoint from last delivered brief; omit initially for baseline.
currencies––morning: 1-10 customer currency codes from data_catalogue, required.
currencystring|null–Catalogue currency code; optional for spoken. Morning uses currencies instead.
depthstring–brief: currency summary; indicator: trend and catalysts; regime: macro regime; research_pack: indicator context; spoken: news to read aloud; morning: changes since last brief.
end_datestring|null–History upper bound YYYY-MM-DD; ignored by brief, spoken, morning.
indicatorstring|null–Catalogue slug; required for indicator and research_pack depths.
quotestring|null–research_pack only: pair quote currency.
sincestring|null–morning: last-delivery ISO 8601 with UTC offset; only without checkpoint.
start_datestring|null–History lower bound YYYY-MM-DD; ignored by brief, spoken, morning.
timezonestring|null–morning: customer IANA timezone, required.

No output schema declared.

No examples provided.

macro_heatmap_task ~281

Build a macro heatmap, pair cockpit or Macro Monitor. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
basestring|null–mode='war_room' only: pair base currency, 3-letter code.
currenciesstring|null–Comma-separated 3-letter currency codes (lowercase preferred). Supported values include: lowercase 3-letter catalogue currency, e.g. usd or eur.
currencystring|null–mode='war_room' only: spotlight currency. Defaults to usd.
end_datestring|null–Optional inclusive upper bound, YYYY-MM-DD.
indicatorstring|null–mode='war_room' only: spotlight indicator. Defaults to inflation.
indicatorsstring|null–Comma-separated indicator slugs to include in the matrix. Supported values include: catalogue indicator slug, e.g. inflation or policy_rate.
modestring–heatmap: cross-currency matrix; war_room: single-pair cockpit; monitor: histories, FX, coverage and releases.
quotestring|null–mode='war_room' only: pair quote currency. Defaults to usd.
start_datestring|null–Optional inclusive lower bound, YYYY-MM-DD.
timezonestring–Monitor display timezone, an IANA name.

No output schema declared.

No examples provided.

macro_news ~180

Return recent official central-bank news and press-release headlines for a currency, covering central-bank policy, inflation, employment, GDP, trade, fiscal, energy, and commodity narratives. Rows are official-source headlines with lightweight keyword-derived affected_indicators and sentiment fields when a headline is classifiable. Supported currencies: lowercase 3-letter catalogue currency, e.g. usd or eur. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
currencystringyes3-letter ISO currency code (case-insensitive). Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
limitinteger–Maximum number of headline rows to request.
lookback_daysinteger–Maximum age of returned headlines in calendar days when headline timestamps are available.
offsetinteger–Zero-based headline offset.
NameTypeReqDescription
resultobjectyes–

No examples provided.

market_sessions ~128

Returns which FX trading sessions are currently open (Sydney, Tokyo, London, New York) and when the next session opens or closes, for questions such as 'is the market open?', 'when does London open?', or 'which sessions overlap right now?'. An ISO-8601 UTC timestamp in `at` returns the snapshot for a specific moment instead of now. Accounts for weekends and major banking holidays. Access: free, no API key required.

NameTypeReqDescription
atstring|null–Optional ISO-8601 UTC timestamp; defaults to now. Use to snapshot session state at a specific moment.
NameTypeReqDescription
resultobjectyes–

No examples provided.

mcp_capabilities ~124

Explains what the FXMacroData MCP server can do: which tools render MCP Apps, which return plain rows, what is public versus subscriber-only, and how tool selection differs across ChatGPT, Claude, Cursor, Codex, and plain MCP clients. Suited to questions about what is available, why visuals are not showing, or how to get the same result in a different interface.

NameTypeReqDescription
topicstring–overview (default) explains tools, visuals and access; auth explains whether to use OAuth, an API key or a bearer token for a given client.

No output schema declared.

No examples provided.

official_datasets ~387

One reader for the official datasets outside the headline indicators. `family` picks the set: financial_prices (government yield curves, securities, overnight benchmarks; by currency), native_history (gold ownership and custody, Treasury auctions, cash and debt, TIC positions, EIA energy; by source and year), official_dataset (balance of payments, international investment position, capital flows, central-bank liquidity, FX intervention, auctions, external debt, credit conditions, wage settlements; by dataset and currency) and company_results (company trading updates as macro evidence; by country). Omit the selector to list what a family holds. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
countrystring|null–company_results only: two-letter ISO country code. Omit to list countries.
currencystring|null–3-letter currency code for financial_prices and official_dataset.
datasetstring|null–official_dataset only: the dataset slug, for example bop or cb_liquidity.
end_datestring|null–Inclusive upper bound, YYYY-MM-DD.
familystringyesWhich dataset family to read.
filters––Family-specific filters. financial_prices: measure, instrument_id, issuer. native_history: measure, holder_country_code, ownership_basis, maturity, account_type, order, region, product. official_data…
limit––Rows per page (1-100).
offset––Zero-based row offset, e.g. 0 for the first page.
sourcestring|null–financial_prices or native_history: the source id. Omit on native_history to list sources.
start_datestring|null–Inclusive lower bound, YYYY-MM-DD.
year––native_history only: the year to read.
NameTypeReqDescription
resultobjectyes–

No examples provided.

organisation_profile ~82

Read one sourced public organisation summary by slug, including services, original sources and a canonical FXMacroData citation URL. Directory references carry no claim of regulatory approval or endorsement. No claim evidence or contact records are returned. Access: one public organisation summary, no API key required.

NameTypeReqDescription
slugstringyesExact lowercase hyphenated organisation slug from a directory search result.
NameTypeReqDescription
resultobjectyes–

No examples provided.

organisation_search ~117

Find publication-cleared FX industry organisations by name or service, optionally within a business category. Returns at most ten directory references with canonical citation URLs; does not rank firms or export the database. Access: public directory references, no API key required.

NameTypeReqDescription
categorystring|null–Exact business category ID from directory results; omit to search all categories.
limitinteger–Maximum directory references, 1-10.
querystringyesOrganisation name or service search, 2-120 characters, e.g. currency exchange.
NameTypeReqDescription
resultobjectyes–

No examples provided.

ping ~28

Health check that confirms the FXMacroData API and MCP server are reachable. Returns the API health response.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultobjectyes–

No examples provided.

plot_visual_artifact ~692

Build a generic MCP Apps chart: single or multi-series charts, including actual-vs-consensus views combining announcements with predictions. Rate-differential plots show both policy rates and their spread. Charts FXMacroData data only; no arbitrary URLs or custom code. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
basestring|null–Base currency for single-series forex plots. Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
chart_kindstring–Initial chart view. Supported: line, area, bar, dot, step.
currencystring|null–Single-series currency for announcements, predictions, or COT. Supported macro currencies: lowercase 3-letter catalogue currency, e.g. usd or eur. Supported COT currencies: AUD, CAD, CHF, EUR, GBP, J…
end_datestring|null–Inclusive upper bound, YYYY-MM-DD.
indicatorstring|null–Single-series indicator for announcements, predictions, or commodities. Supported macro indicators: catalogue indicator slug, e.g. inflation or policy_rate. Supported commodity indicators: crude_oil_…
limitinteger–Maximum rows per source. Defaults to 20; maximum 100.
offsetinteger–Zero-based row offset per source.
page––One-based page number per source.
prediction_sourcestring|null–Optional prediction source filter for prediction series.
prediction_typestring|null–Optional legacy prediction-type filter for prediction series. Superseded by prediction_class.
querystring|null–Optional natural-language request to preserve in the payload title/context.
quotestring|null–Quote currency for single-series forex plots. Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
series––Optional list of series specs. Each spec supports `source` (announcements, predictions, forex, commodities, cot), `currency`, `indicator`, `base`, `quote`, `label`, `y_key`, `metric`, `prediction_cla…
sourcestring|null–Single-series source when `series` is omitted. Supported values: announcements, predictions, forex, commodities, cot, rate_differential (needs base and quote).
start_datestring|null–Inclusive lower bound, YYYY-MM-DD.
titlestring|null–Optional chart title. Defaults to query or an auto-generated title.
x_axisstring–Field to use as the shared x-axis. Supported: date, announcement_datetime, announcement_datetime_local, generated_at, observation_datetime.
y_keystring|null–Single-series metric field. Defaults by source: val for announcements and commodities, predicted_value for predictions, rate for forex, noncommercial_net for COT.
y_labelstring|null–Optional y-axis label for the chart.

No output schema declared.

No examples provided.

press_releases ~91

Return the public central-bank press-release archive for a currency as the original official release rows, without derived sentiment or indicator classifications. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
currencystringyes3-letter ISO currency code (case-insensitive).
limitinteger–Maximum rows to return.
offsetinteger–Zero-based row offset.
NameTypeReqDescription
resultobjectyes–

No examples provided.

rate_curve ~138

Return official government-nominal curve nodes, slopes, or derived forward segments for one currency. This is a subscriber data tool and preserves the endpoint's requested view and method metadata. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
currencystringyes3-letter currency code.
curve_familystring–Official curve family.
datestring|null–Optional target date, YYYY-MM-DD.
methodstring–Forward derivation method when view is forwards.
metricstring–Curve metric.
viewstring–Curve view: tenor nodes, slopes or forward rates.
NameTypeReqDescription
resultobjectyes–

No examples provided.

rate_differentials ~210

Return the stored or derived rate differential for one FX pair, with the measure, rate type, curve family, and tenor metadata that define it. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
basestringyesBase currency code.
curve_familystring–Curve family when rate_type is forward.
end_datestring|null–Optional inclusive end date, YYYY-MM-DD.
end_tenor_yearsnumber–End tenor in years for forward differentials.
limitinteger–Maximum rows to return.
measurestring–Shared rate measure to compare across the pair.
offsetinteger–Zero-based row offset.
quotestringyesQuote currency code.
rate_typestring–Differential type.
start_datestring|null–Optional inclusive start date, YYYY-MM-DD.
start_tenor_yearsnumber–Start tenor in years for forward differentials.
NameTypeReqDescription
resultobjectyes–

No examples provided.

release_calendar ~517

Get upcoming scheduled macroeconomic release timestamps for a currency, for questions such as when the next CPI, GDP, payrolls, or policy decision is due. Returns ISO-8601 announcement_datetime values in UTC plus market-local timestamps, a markdown agenda, and Release Calendar App metadata. The optional `timezone` adds an `announcement_datetime_requested_timezone` field. Each row has a `release` string with the indicator name and a `currency` code. Unbounded calls return future releases only. The optional `indicator` filter narrows to a single series, and optional `start_date` and `end_date` bounds select a month, week, day, or explicit date range. Supported currencies: lowercase 3-letter catalogue currency, e.g. usd or eur. The `indicator` parameter lists the accepted indicator slugs. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
archive_event_idstring|null–versions only: the archive event_id from snapshot rows.
as_ofstring|null–snapshot and archive_coverage: ISO 8601 knowledge cutoff ending in Z or an offset.
checkpoint––snapshot/versions: checkpoint from the first page.
currencystringyes3-letter ISO currency code (case-insensitive). Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
cursorstring|null–snapshot/versions: next_cursor from the previous page.
end_datestring|null–Optional inclusive upper bound, YYYY-MM-DD.
event_kindstring|null–snapshot only: event kind filter.
importancestring|null–snapshot only: importance filter.
indicatorstring|null–Optional indicator slug to narrow results. Supported: catalogue indicator slug, e.g. inflation or policy_rate.
knowledge_modestring|null–snapshot only: accepted (default) or reconstruction.
limit––snapshot/versions: page size, default 250.
start_datestring|null–Optional inclusive lower bound, YYYY-MM-DD.
timezonestring|null–Optional IANA timezone for an additional converted timestamp, for example America/Sao_Paulo.
viewstring–upcoming (default): scheduled releases. snapshot: the schedule as it was known at `as_of`. versions: every schedule change and cancellation for one `archive_event_id`. archive_coverage: what we captu…

No output schema declared.

No examples provided.

release_calendar_visual_artifact ~271

Returns the release calendar payload with MCP Apps metadata so compatible clients render the interactive Release Calendar App inline. Suited to requests to show, display, visualize, or render a macro release calendar, such as 'show me the AUD release calendar'. Optional `indicator`, `start_date`, and `end_date` filters narrow the calendar to a series, month, week, day, or date range; `timezone` adds local times for a specific city or region. Supported currencies: lowercase 3-letter catalogue currency, e.g. usd or eur. The `indicator` parameter lists the accepted indicator slugs. Access: USD needs no API key; other currencies return subscription_required with a subscribe link.

NameTypeReqDescription
currencystringyes3-letter ISO currency code (case-insensitive). Supported: lowercase 3-letter catalogue currency, e.g. usd or eur.
end_datestring|null–Optional inclusive upper bound, YYYY-MM-DD.
indicatorstring|null–Optional indicator slug to narrow results. Supported: catalogue indicator slug, e.g. inflation or policy_rate.
start_datestring|null–Optional inclusive lower bound, YYYY-MM-DD.
timezonestring|null–Optional IANA timezone for an additional converted timestamp, for example America/Sao_Paulo.

No output schema declared.

No examples provided.

research_paper_append_journal ~160

Append a version-linked journal note; does not modify existing notes. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
bodystringyesJournal note text, 1-6000 characters; no credentials.
book_idstringyes32 lowercase hex paper-account ID from an owned account result.
event_idstring|null–Optional paper event ID from this version; omit for an unlinked note.
kindstringyesJournal note category: hypothesis, observation, decision or review.
version_idstringyesExact version_id belonging to this paper account, copied from its read result.

No output schema declared.

No examples provided.

research_paper_archive ~97

Archive a paper account and its active version. This account cannot be resumed. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
book_idstringyes32 lowercase hex paper-account ID from an owned account result.
expected_versionstringyesCurrent version_id returned by the account read; rejects stale updates.

No output schema declared.

No examples provided.

research_paper_events ~97

Read paged paper event summaries; full input evidence remains in the private audit export. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
book_idstringyes32 lowercase hex paper-account ID from an owned account result.
offsetinteger–Zero-based row offset; 0 starts the first page.

No output schema declared.

No examples provided.

research_paper_flatten ~109

Request paper position flattening and discard pending orders; new entries stay paused until the account is resumed. This changes simulated account state. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
book_idstringyes32 lowercase hex paper-account ID from an owned account result.
expected_versionstringyesCurrent version_id returned by the account read; rejects stale updates.

No output schema declared.

No examples provided.

research_paper_journal ~94

Read five journal notes per offset, with long text explicitly shortened. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
book_idstringyes32 lowercase hex paper-account ID from an owned account result.
offsetinteger–Zero-based row offset; 0 starts the first page.

No output schema declared.

No examples provided.

research_paper_list ~48

List owned reference paper accounts. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

research_paper_pause ~87

Pause new paper entries. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
book_idstringyes32 lowercase hex paper-account ID from an owned account result.
expected_versionstringyesCurrent version_id returned by the account read; rejects stale updates.

No output schema declared.

No examples provided.

research_paper_read ~71

Read one reference paper account and its versions. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
book_idstringyes32 lowercase hex paper-account ID from an owned account result.

No output schema declared.

No examples provided.

research_paper_resume ~89

Resume paper entries unless risk halted. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
book_idstringyes32 lowercase hex paper-account ID from an owned account result.
expected_versionstringyesCurrent version_id returned by the account read; rejects stale updates.

No output schema declared.

No examples provided.

research_paper_revise_journal ~205

Append a new revision of an existing journal note, retaining the previous revisions. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
bodystringyesJournal note text, 1-6000 characters; no credentials.
book_idstringyes32 lowercase hex paper-account ID from an owned account result.
entry_idstringyesExisting journal entry ID: 32 lowercase hex characters, copied from the journal.
event_idstring|null–Optional paper event ID from this version; omit for an unlinked note.
expected_revisionintegeryesCurrent integer revision returned by the journal; rejects stale revisions.
kindstringyesJournal note category: hypothesis, observation, decision or review.
version_idstringyesExact version_id belonging to this paper account, copied from its read result.

No output schema declared.

No examples provided.

research_paper_start ~188

Create a new reference paper account starting flat at USD 100. Replay is historical. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
labelstringyesAccount/version display label, 1-80 characters; no credentials.
limits––Optional risk object: allocation (0,1], max_drawdown_pct 1-50, max_reference_age_days integer 1-7. Defaults: 1, 20, 4.
modestring–forward observes new reference inputs; replay simulates saved historical inputs.
request_idstringyesIdempotency ID: 32 lowercase hex characters; reuse only when retrying the same request.
run_idstringyes32 lowercase hex study ID from an owned run result.

No output schema declared.

No examples provided.

research_paper_start_version ~245

Archive the current version and start a fresh immutable version flat at USD 100. Discards its active position and pending order without a synthetic closing fill; preserves history. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
book_idstringyes32 lowercase hex paper-account ID from an owned account result.
expected_versionstringyesCurrent version_id returned by the account read; rejects stale updates.
labelstringyesAccount/version display label, 1-80 characters; no credentials.
limits––Optional risk object: allocation (0,1], max_drawdown_pct 1-50, max_reference_age_days integer 1-7. Defaults: 1, 20, 4.
modestring–forward observes new reference inputs; replay simulates saved historical inputs.
request_idstringyesIdempotency ID: 32 lowercase hex characters; reuse only when retrying the same request.
run_idstringyes32 lowercase hex study ID from an owned run result.

No output schema declared.

No examples provided.

research_run_cancel ~79

Cancel a saved research job. Cancellation cannot be undone; completed work may need a new submission. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
run_idstringyes32 lowercase hex study ID from an owned run result.

No output schema declared.

No examples provided.

research_run_list ~46

List owned saved studies. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

research_run_read ~74

Read one saved study; full report is available in the Research App. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
run_idstringyes32 lowercase hex study ID from an owned run result.

No output schema declared.

No examples provided.

research_run_reveal_holdout ~88

Irreversibly expose a study holdout and record its exposure. The holdout can no longer be treated as unseen. Requires FXMacroData account access; owner-only. No live orders or model inference. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
run_idstringyes32 lowercase hex study ID from an owned run result.

No output schema declared.

No examples provided.

Install

How do I install the FXMacroData MCP server?

FXMacroData is a hosted endpoint at https://fxmacrodata.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · fxmacrodata.com

# add to Claude Code
claude mcp add --transport http fxmacrodata-fxmacrodata 'https://fxmacrodata.com/mcp'
Common questions

What is the FXMacroData MCP server?

FXMacroData is an MCP server listed in the public MCP registry as io.github.fxmacrodata/fxmacrodata. Macroeconomic and FX time-series data for AI agents: indicators, calendars, COT, forex, commodities. This page covers its hosted endpoint (https://fxmacrodata.com/mcp).

Is the FXMacroData MCP server safe to use?

FXMacroData scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the FXMacroData MCP server expose?

FXMacroData exposes 52 tools: ping, mcp_capabilities, subscribe_for_mcp_access, data_catalogue, risk_sentiment, and 47 more. Their descriptions and schemas cost roughly 11,117 tokens of context every time the server is loaded.

Does the FXMacroData MCP server require authentication?

No. We connected to FXMacroData without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the FXMacroData MCP server still maintained?

FXMacroData is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the FXMacroData MCP server?

VerifyMCP ran 14 checks on FXMacroData, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.