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
research_run_submit ~197

Queue one bounded research calculation; returns a queued run ID. 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
configurationobjectyesResearch settings: base, quote (ISO codes), start_date, end_date (YYYY-MM-DD); optional series (up to six {currency, indicator, period_aggregation?}), price_fields, mode, decision_frequency, decision…
kindstring–Study type: chart, backtest, correlation, carry, screener, events or experiment.
request_idstring|null–Optional idempotency key: 16-64 letters, digits or hyphens; reuse only for identical retries.

No output schema declared.

No examples provided.

risk_sentiment ~180

Return the global risk-on/risk-off sentiment series used for FX regime analysis. The result includes a derived composite score, regime label, component contributions, pagination, and data_quality metadata. Suited to cross-asset regime context for high-beta, safe-haven, commodity, or USD-defensive FX conditions. Access: free, no API key required.

NameTypeReqDescription
after_sequence––changes only: return changes after this sequence.
end_datestring|null–Optional inclusive end date in YYYY-MM-DD format.
limit––changes only: page size, default 20.
start_datestring|null–Optional inclusive start date in YYYY-MM-DD format.
viewstring–series (default): the score history. changes: a resumable feed of recorded additions and revisions; pass pagination.next_after_sequence back as after_sequence.
NameTypeReqDescription
resultobjectyes–

No examples provided.

seasonality ~198

Get monthly return seasonality for an FX pair or XAU/USD, covering seasonal patterns, month-of-year tendency, historical monthly win rate, and XAUUSD/gold seasonality. Returns monthly average return, median return, win rate, sample size, dispersion, and per-year monthly returns from stored FX or gold series. Access: API key required, else returns subscription_required with a subscribe link.

NameTypeReqDescription
end_datestring|null–Inclusive upper bound, YYYY-MM-DD. Defaults to today.
instrumentstringyesSix-letter pair such as EURUSD, AUDUSD, USDJPY, or XAUUSD. Slashes and separators are accepted by the REST endpoint only when passed as a single string.
lookback_yearsinteger|null–Number of years to include, 2-30. Defaults to 10.
monthstring|null–Optional month filter, 1-12 or name such as July.
NameTypeReqDescription
resultobjectyes–

No examples provided.

subscribe_for_mcp_access ~35

Returns FXMacroData subscription options and a direct checkout path for unlocking MCP app visuals, charts, and advanced analytical tools.

Input schema present but exposes no named parameters.

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.