Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Changed the definition of "get_historical_analogs", "get_historical_reaction_context" and "get_upcoming_risks"
⟨131 unchanged words⟩ surprise -distance approach as US_CPI (pce-historical-analog-v1). Target period: if referencePeriod is omitted, the target is the most recent event of the requested type. Surprises are never estimated, so if that event has no verified pre-release consensus (common right after a new NFP release) the tool fails with NO_VERIFIED_PRE_RELEASE_EXPECTATION. The error details include targetReferencePeriod, latestReleasedPeriod, latestPeriodWithVerifiedExpectation and a hint; to analyze that prior period, retry with referencePeriod=YYYY-MM. Tell the user the newest release could not be analyzed rather than presenting the prior period as the latest. Every "cannot compute" error has the same shape: "CODE: reason [hint] details={json}", where the JSON always contains code, eventType and hint. Do NOT use this tool when the user's ⟨30 unchanged words⟩
⟨60 unchanged words⟩ 2024-06 or 2026-08). If omitted, thelatestmostavailablerecent event isresolvedtheastarget. Use it to analyze a prior period when thetarget.latest event has no verified pre-release expectation.","type":"string"}},"required": ⟨3 unchanged words⟩
⟨96 unchanged words⟩ uses target-relative robust scale normalization (nfp-historical-analog-v1). Target period: if referencePeriod is omitted, the target is the most recent event of the requested type. Surprises are never estimated, so if that event has no verified pre-release consensus (common right after a new NFP release) the tool fails with NO_VERIFIED_PRE_RELEASE_EXPECTATION. The error details include targetReferencePeriod, latestReleasedPeriod, latestPeriodWithVerifiedExpectation and a hint; to analyze that prior period, retry with referencePeriod=YYYY-MM. Tell the user the newest release could not be analyzed rather than presenting the prior period as the latest. Every "cannot compute" error has the same shape: "CODE: reason [hint] details={json}", where the JSON always contains code, eventType and hint. Do NOT use this tool when the user's ⟨51 unchanged words⟩
⟨63 unchanged words⟩ 2024-06 or 2026-08). If omitted, thelatestmostavailablerecent event isusedtheastarget. Use it to analyze a prior period when
⟨40 unchanged words⟩ is happening in the next 24 hours, this week, or over the next month, what upcoming macro risks or scheduled events exist, or when the next CPI, next NFP, next PCE, next Fed, next ECB, next BoE ⟨6 unchanged words⟩ supported risks are U.S. CPI releases, U.S. Nonfarm Payrolls releases, U.S. PCE inflation releases, Federal Reserve monetary-policy decisions, ⟨6 unchanged words⟩ monetary-policy decisions, and Bank of Japan monetary-policy decisions. The horizon can extend up to 720 hours (30 days). scheduleCoverage reports, for each supported event type, the latest known scheduled date and whether the known calendar covers the whole window. If scheduleCoverageComplete is false, some event types may have additional events in the window that are not yet known; say so instead of treating the list as complete. Results are based on official release calendars and ⟨34 unchanged words⟩
⟨8 unchanged words⟩ window in hours. Defaults to 24. Maximum is168720 (730
Changed the definition of "get_event_context"
RetrieveGetsource-groundedtheeventofficialcontextactual values, pre-release market consensus, and surprise forsupporteda specific U.S. macroreleasesdataincludingrelease: CPI (US_CPI), Nonfarm Payrolls / jobs report (
Changed the definition of "get_historical_analogs", "get_market_reaction" and "get_upcoming_risks"
⟨59 unchanged words⟩ and US_NONFARM_PAYROLLS across EURUSD, GBPUSD, and USDJPY. US_PCE is recognized but not yet publicly available: the historical PCE calibration corpus currently has too few usable periods, and a request for US_PCE returns a structured INSUFFICIENT_HISTORICAL_CALIBRATION error (with usable/required event counts) instead of analog results until the corpus grows. Similarity methodology is event-specific: US_CPI uses headline/core surprise distance; US_NONFARM_PAYROLLS uses target-relative robust scale normalization (nfp-historical-analog-v1); US_PCE (once activated) uses the same raw surprise -distance approach as US_CPI (pce-historical-analog-v1). Do NOT use this tool when the ⟨31 unchanged words⟩
⟨5 unchanged words⟩ {"description":"Canonical target event type: US_CPI, US_NONFARM_PAYROLLS,
Certificate recorded, valid to 2026-12-10
Authorization not required
Changed the definition of "get_historical_analogs"
⟨8 unchanged words⟩ "string"}},"type":"object"},"CpiMetricSurprise":{"properties":{"calculationBasis":{"enum":["REPORTED_ACTUAL_MINUS_EXPECTATION","DERIVED_ACTUAL_MINUS_EXPECTATION"],"type":"string"},"capturedAt":{"format":"date-time","type":"string"},"consensus":{"type":"number"},"derivedActual":{"type":"number"},"direction":{"enum":["ABOVE_EXPECTATION","BELOW_EXPECTATION","IN_LINE"],"type":"string"},"provider":{"type":"string"},"reportedActual":{"type":"number"},"surprise":{"type":"number"},"unit":{"type":"string"}},"required":["consensus","direction","reportedActual","surprise","unit"],"type":"object"},"ReactionWindowType":{"enum":["M5","M15" ⟨89 unchanged words⟩ ],"type":"string"},"surpriseProfile":{"properties":{"coreMom":{"$ref":"#/$defs/CpiMetricSurprise"},"coreYoy":{"$ref":"#/$defs/CpiMetricSurprise"},"headlineMom":{"$ref":"#/$defs/CpiMetricSurprise"},"headlineYoy":{"$ref":"#/$defs/CpiMetricSurprise"}},"type":"object"},"totalSurpriseDistance":{"type":"number"}} ⟨180 unchanged words⟩
First tool surface recorded: 6 tools (server version 0.6.0)
Unknown → Live
https://fx.coco-pier.com/mcp (mcp_streamable_http) — from mcp_registry, with the record
Showing the latest 9 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
{"$defs":{"ScheduledEventType":{"enum":["US_CPI","US_NONFARM_PAYROLLS","US_PCE","FEDERAL_RESERVE","ECB","BANK_OF_ENGLAND","BANK_OF_JAPAN"],"type":"string"}},"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"asOf ⟨19 unchanged words⟩ ,"type":"array"},"eventType":{"enum":["US_CPI","US_NONFARM_PAYROLLS","US_PCE","FEDERAL_RESERVE","ECB","BANK_OF_ENGLAND","BANK_OF_JAPAN"],"type$ref":"string#/$defs/ScheduledEventType"},"importance":{"enum":["HIGH" ⟨55 unchanged words⟩ :"object"},"type":"array"},"scheduleCoverage":{"items":{"properties":{"coversWindow":{"type":"boolean"},"eventType":{"$ref":"#/$defs/ScheduledEventType"},"latestKnownScheduledAt":{"format":"date-time","type":"string"}},"required":["coversWindow","eventType"],"type":"object"},"type":"array"},"scheduleCoverageComplete":{"type":"boolean"},"windowEnd":{"format":"date-time","type": ⟨2 unchanged words⟩ :["asOf","horizonHours","instrument","risks","scheduleCoverage","scheduleCoverageComplete","windowEnd"],"type":"object"}
⟨5 unchanged words⟩ {"description":"Canonical financial event type.\n\nSupported values:\nUS_CPI\nUS_NONFARM_PAYROLLS\nUS_PCE\n\nUse\nUS_CPI (Consumer Price Index; headline and core CPI)\nUS_NONFARM_PAYROLLS (NFP / jobs report; payrolls, unemployment rate, average hourly earnings)\nUS_PCE (PCE / core PCE price index)\n\nUse these values exactly.","type":"string"} ⟨28 unchanged words⟩
⟨44 unchanged words⟩ "observations":{"items":{"properties":{"consensusStatus":{"description":"Why the expectation block is present or absent: AVAILABLE, NOT_AVAILABLE, NOT_FOUND, NOT_CAPTURED, EXCLUDED_POST_RELEASE or NOT_APPLICABLE.","enum":["AVAILABLE","NOT_AVAILABLE","NOT_FOUND","NOT_CAPTURED","EXCLUDED_POST_RELEASE","NOT_APPLICABLE"],"type":"string"},"consensusStatusDetail":{"description":"Human-readable explanation of consensusStatus.","type":"string"},"derivationMethod":{"type":"string"},"derivedActual" ⟨2 unchanged words⟩ "expectation":{"properties":{"capturedAt":{"description":"When the consensus snapshot was captured; always before releaseCutoffAt.","format":"date-time","type":"string"},"consensus":{"type":"string"},"releaseCutoffAt":{"description":"Instant the consensus was validated against (capturedAt must be strictly earlier).","format":"date-time","type":"string"},"releaseCutoffBasis":{"description":"Which event timestamp the cutoff came from: RELEASED_AT, or SCHEDULED_AT when the actual release time is not yet recorded.","type":"string"},"source":{"$ref":"#/$defs/SourceContextResponse"}},"required ⟨15 unchanged words⟩ "string"},"revised":{"type":"boolean"},"revisionStatus":{"description":"Revision state supported by stored vintages: REVISED, UNCHANGED, or NOT_CAPTURED (only the initial vintage is stored; revision state unknown).","enum":["REVISED","UNCHANGED","NOT_CAPTURED"],"type":"string"},"surprise":{"properties":{"basis" ⟨79 unchanged words⟩
⟨13 unchanged words⟩ statement. Specify the targetType, such as US_CPI, US_PCE (alias PCE), US_NONFARM_PAYROLLS (alias NFP), FEDERAL_RESERVE, ECB, BANK_OF_ENGLAND ⟨5 unchanged words⟩ BOJ). Optionally specify dateOrPeriod: - For US_CPI, US_PCE, and US_NONFARM_PAYROLLS: reference period in YYYY-MM format ⟨85 unchanged words⟩
⟨5 unchanged words⟩ description":"Optional reference period (YYYY-MM for US_CPI, US_PCE, and US_NONFARM_PAYROLLS) or statement date (YYYY-MM-DD for ⟨27 unchanged words⟩ {"description":"Canonical target event type: US_CPI, US_PCE (alias PCE), US_NONFARM_PAYROLLS (alias NFP), FEDERAL_RESERVE, ECB, ⟨14 unchanged words⟩
⟨54 unchanged words⟩ exist, or when the next CPI, next PCE, next Fed, next ECB, next BoE, or next BoJ event occurs. The supported risks are U.S. CPI releases, U.S. PCE inflation releases, Federal Reserve monetary-policy decisions, ECB monetary-policy ⟨54 unchanged words⟩
⟨27 unchanged words⟩ :{"enum":["US_CPI","US_NONFARM_PAYROLLS","US_PCE","FEDERAL_RESERVE","ECB","BANK_OF_ENGLAND","BANK_OF_JAPAN"], ⟨76 unchanged words⟩