此 MCP 可以做什么
Monitors WooCommerce checkout and payment-path health, diagnoses revenue incidents, and verifies recovery after changes.
功能
工具
4
工具
check_checkout_change_risk
Is this change likely to break checkout?
Answers: is a change to this store's checkout or payment path known to have broken revenue elsewhere — before it is applied, or when explaining a change that was already made? Checks a component and version against public release and issue evidence scoped to the money path (payment capture, order status transitions, gateway webhooks, wallet checkout), not to general plugin update safety. With no component named, checks every commerce change this store has made recently. Says `unknown` when nothing independent is on record — an absence of reports is not a safety record, and is reported as the absence it is. Free.
只读
可访问外部资源
幂等
输入模式
{'type': 'object', 'properties': {'component': {'type': 'string', 'maxLength': 80, 'description': 'e.g. "plugin:woocommerce-gateway-stripe". Omit to check this store\'s own recent changes.'}, 'to_version': {'type': 'string', 'maxLength': 40}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['checked', 'source', 'billable', 'price_micros'], 'properties': {'source': {'enum': ['named_component', 'store_recent_changes'], 'type': 'string'}, 'checked': {'type': 'array', 'items': {'type': 'object', 'required': ['component', 'to_version', 'verdict', 'reason', 'independent_source_count', 'affected_versions', 'fixed_version', 'source_urls'], 'properties': {'reason': {'type': 'string'}, 'verdict': {'enum': ['known_risk', 'no_known_risk', 'unknown'], 'type': 'string'}, 'component': {'type': 'string'}, 'to_version': {'type': ['string', 'null']}, 'source_urls': {'type': 'array', 'items': {'type': 'string'}}, 'fixed_version': {'type': ['string', 'null']}, 'affected_versions': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}}, 'independent_source_count': {'type': 'integer'}}, 'additionalProperties': False}}, 'billable': {'type': 'boolean'}, 'price_micros': {'type': 'integer'}}, 'additionalProperties': False}
diagnose_revenue_incident
Why did this store's checkout revenue break?
Answers: what most likely broke this store's checkout or payment path, what argues against each explanation, and how to tell whether a fix actually held. Joins the store's own privacy-safe signals — order status over time, order-status transitions, order-note reason codes, gateway and webhook health, scheduler backlog, checkout page health, recent plugin/theme/core changes — against public release and issue evidence, on one timeline. Every answer reports which signal families this store could and could not report, because a family that cannot be collected is not a family that is fine. Returns up to three ranked hypotheses, each with the observations behind it, independent public sources where they exist, counterevidence, what remains unknown, safe next steps, and a verification plan. Returns `abstained` and charges nothing when the snapshot is stale, coverage is thin, or the signals do not support any cause — an unsupported guess during an outage is worse than no answer. Free while in beta. Call get_checkout_health_snapshot first.
只读
可访问外部资源
幂等
输入模式
{'type': 'object', 'properties': {'symptom': {'enum': ['orders_dropped', 'payment_succeeded_order_pending', 'failed_orders_spiked', 'payment_method_missing', 'checkout_errors', 'unknown'], 'type': 'string', 'description': 'What the merchant reports. Use "unknown" rather than guessing.'}, 'window_seconds': {'type': 'integer', 'maximum': 604800, 'minimum': 900, 'description': 'Window in seconds. Default 86400 (24h), maximum 604800 (7d).'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['symptom', 'window', 'data_freshness', 'coverage', 'timeline', 'failure_pattern', 'failure_pattern_reasoning', 'hypotheses', 'abstained', 'billable', 'price_micros'], 'properties': {'window': {'type': 'object', 'required': ['started_at', 'ended_at'], 'properties': {'ended_at': {'type': 'integer'}, 'started_at': {'type': 'integer'}}, 'additionalProperties': False}, 'symptom': {'type': 'string'}, 'billable': {'type': 'boolean'}, 'coverage': {'type': 'object', 'required': ['families', 'present', 'missing', 'sufficient', 'unavailable', 'truncated', 'no_history_yet', 'not_collected', 'caveat'], 'properties': {'caveat': {'type': ['string', 'null'], 'description': 'One sentence naming why the missing families are missing.'}, 'missing': {'type': 'array', 'items': {'type': 'string'}}, 'present': {'type': 'array', 'items': {'type': 'string'}}, 'families': {'type': 'integer', 'description': 'How many families actually reported. Only these can corroborate anything.'}, 'truncated': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Reported, but hit a collection cap — a PARTIAL aggregate covering fewer events than were asked for. A burst is what overflows a cap, so this is likeliest exactly when it matters.'}, 'sufficient': {'type': 'boolean'}, 'unavailable': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Cannot be collected on this store at all. Silence here is not evidence of health.'}, 'not_collected': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Deliberately not collected in this release.'}, 'no_history_yet': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only know what has happened since the plugin was connected.'}}, 'additionalProperties': False}, 'timeline': {'type': 'array', 'items': {'type': 'object', 'required': ['at', 'kind', 'statement'], 'properties': {'at': {'type': 'integer'}, 'kind': {'type': 'string'}, 'statement': {'type': 'string'}}, 'additionalProperties': False}}, 'abstained': {'type': ['object', 'null'], 'required': ['reason'], 'properties': {'reason': {'type': 'string'}}, 'additionalProperties': False}, 'hypotheses': {'type': 'array', 'items': {'type': 'object', 'required': ['rank', 'hypothesis', 'confidence', 'observations', 'public_evidence', 'counterevidence', 'unknowns', 'safe_next_steps', 'verification_plan', 'billing_eligibility'], 'properties': {'rank': {'type': 'integer'}, 'unknowns': {'type': 'array', 'items': {'type': 'string'}}, 'confidence': {'enum': ['high', 'medium', 'low', 'abstained'], 'type': 'string'}, 'hypothesis': {'type': 'string'}, 'observations': {'type': 'array', 'items': {'type': 'object', 'required': ['kind', 'statement', 'at', 'weight'], 'properties': {'at': {'type': ['integer', 'null']}, 'kind': {'type': 'string'}, 'weight': {'enum': ['strong', 'supporting'], 'type': 'string'}, 'statement': {'type': 'string'}}, 'additionalProperties': False}}, 'counterevidence': {'type': 'array', 'items': {'type': 'string'}}, 'public_evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['url', 'source_type', 'origin_group', 'observed_at', 'affected_version', 'fixed_version'], 'properties': {'url': {'type': 'string'}, 'observed_at': {'type': 'integer'}, 'source_type': {'type': 'string'}, 'origin_group': {'type': 'string'}, 'fixed_version': {'type': ['string', 'null']}, 'affected_version': {'type': ['string', 'null']}}, 'additionalProperties': False}}, 'safe_next_steps': {'type': 'array', 'items': {'type': 'string'}}, 'verification_plan': {'type': 'string'}, 'billing_eligibility': {'enum': ['billable', 'free_abstained', 'free_insufficient_coverage', 'free_stale'], 'type': 'string'}}, 'additionalProperties': False}}, 'price_micros': {'type': 'integer'}, 'data_freshness': {'enum': ['fresh', 'aging', 'stale'], 'type': 'string'}, 'failure_pattern': {'enum': ['card_testing_suspected', 'buyer_failures', 'mixed_or_unclear'], 'type': 'string'}, 'failure_pattern_reasoning': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}
get_checkout_health_snapshot
Is this store's revenue path healthy right now?
Answers: is anything wrong with this connected WooCommerce store's checkout and payment path right now, and is a full diagnosis worth running? Free, always. Returns order counts by status with the change across the window, gateway/webhook/scheduler health, checkout page health, how many recent commerce changes there were, which signal families this store can and cannot report, and how fresh the underlying data is. Call this FIRST — it is cheap, and `diagnosis_recommended` tells you whether the expensive call would have anything to work with. It returns no customer, order, or payment identifier because the store never sends any.
只读
可访问外部资源
幂等
输入模式
{'type': 'object', 'properties': {'window_seconds': {'type': 'integer', 'maximum': 604800, 'minimum': 900, 'description': 'Window in seconds. Default 86400 (24h), maximum 604800 (7d).'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['connected', 'data_freshness', 'collected_at', 'order_counts', 'paid_order_change_pct', 'gateway_summary', 'webhook_summary', 'error_fingerprints', 'scheduler_overdue', 'recent_changes', 'coverage', 'diagnosis_recommended', 'reason'], 'properties': {'reason': {'type': 'string'}, 'coverage': {'type': 'object', 'required': ['families', 'present', 'missing', 'sufficient', 'unavailable', 'truncated', 'no_history_yet', 'not_collected', 'caveat'], 'properties': {'caveat': {'type': ['string', 'null'], 'description': 'One sentence naming why the missing families are missing.'}, 'missing': {'type': 'array', 'items': {'type': 'string'}}, 'present': {'type': 'array', 'items': {'type': 'string'}}, 'families': {'type': 'integer', 'description': 'How many families actually reported. Only these can corroborate anything.'}, 'truncated': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Reported, but hit a collection cap — a PARTIAL aggregate covering fewer events than were asked for. A burst is what overflows a cap, so this is likeliest exactly when it matters.'}, 'sufficient': {'type': 'boolean'}, 'unavailable': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Cannot be collected on this store at all. Silence here is not evidence of health.'}, 'not_collected': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Deliberately not collected in this release.'}, 'no_history_yet': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only know what has happened since the plugin was connected.'}}, 'additionalProperties': False}, 'connected': {'type': 'boolean'}, 'collected_at': {'type': ['integer', 'null']}, 'order_counts': {'type': 'object', 'additionalProperties': {'type': 'integer'}}, 'data_freshness': {'enum': ['fresh', 'aging', 'stale'], 'type': 'string'}, 'recent_changes': {'type': 'integer'}, 'gateway_summary': {'type': 'object', 'required': ['total', 'unavailable', 'test_mode'], 'properties': {'total': {'type': 'integer'}, 'test_mode': {'type': 'integer'}, 'unavailable': {'type': 'integer'}}, 'additionalProperties': False}, 'webhook_summary': {'type': 'object', 'required': ['total', 'failing', 'disabled'], 'properties': {'total': {'type': 'integer'}, 'failing': {'type': 'integer'}, 'disabled': {'type': 'integer'}}, 'additionalProperties': False}, 'scheduler_overdue': {'type': 'integer'}, 'error_fingerprints': {'type': 'integer'}, 'diagnosis_recommended': {'type': 'boolean'}, 'paid_order_change_pct': {'type': ['integer', 'null'], 'description': 'Change in paid orders across the window; null when there is too little data to compare.'}}, 'additionalProperties': False}
verify_revenue_recovery
Did the fix actually hold?
Answers: after a change was made, did this store's revenue signals actually recover? Compares the window before a stated change against the window since: paid vs pending vs failed order mix, webhook failure counts, and gateway availability. Returns `resolved`, `improving`, `still_failing`, or `unknown` — and `unknown` when too little new data has arrived to tell, which is free. A quiet ten minutes is not a recovery. Free while in beta.
只读
可访问外部资源
幂等
输入模式
{'type': 'object', 'required': ['change_applied_at'], 'properties': {'window_seconds': {'type': 'integer', 'maximum': 604800, 'minimum': 900, 'description': 'Window in seconds. Default 86400 (24h), maximum 604800 (7d).'}, 'change_applied_at': {'type': 'integer', 'description': 'Epoch ms when the fix was applied.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['status', 'reason', 'before', 'after', 'new_regressions', 'billable', 'price_micros'], 'properties': {'after': {'type': ['object', 'null'], 'additionalProperties': True}, 'before': {'type': ['object', 'null'], 'additionalProperties': True}, 'reason': {'type': 'string'}, 'status': {'enum': ['resolved', 'improving', 'still_failing', 'unknown'], 'type': 'string'}, 'billable': {'type': 'boolean'}, 'price_micros': {'type': 'integer'}, 'new_regressions': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}
历史
近期工具变更
已添加
verify_revenue_recovery
2026年9月17日 12:52
已添加
check_checkout_change_risk
2026年9月17日 12:52
已添加
diagnose_revenue_incident
2026年9月17日 12:52
已添加
get_checkout_health_snapshot
2026年9月17日 12:52
发现
类似的 MCP 服务器
amazon-product-research-mcp
com.webotee/amazon-product-research-mcp
Researches Amazon products, brands, sellers, buy-box activity, sourcing profitability, category competition, and supplier opportu…
API Acre
com.apiacre/api-acre
Offers paid APIs for EVM blockchain inspection, data transformation and validation, geocoding, weather, currency conversion, and …
Ask AI
com.ask-ai-data-connector/ask-ai
Answers questions about connected e-commerce data from Shopify, Klaviyo, GA4, Triple Whale, and other sources, covering sales, ma…
Neonjelly
io.neonjelly/mcp
Analyzes Shopify stores, products, apps, traffic, competitors, catalog changes, market cohorts and outreach contacts across a lar…
zobrx
com.zobrx/zobrx
Provides read-only ecommerce operations and analytics for orders, inventory, marketplace performance, advertising, settlements, t…
sella
io.github.sella-network/sella
Operates an agent marketplace for purchasing datasets, APIs, and products, including catalog discovery, purchase settlement, deli…
kurashigram
io.github.Kotaro-Studio/kurashigram
Provides cited Japanese price comparisons, cost-of-living statistics, product prices, shopping data, public benefit information, …
Keepa
io.github.pipeworx-io/keepa
Searches Amazon products and categories and provides price, sales-rank, deal, bestseller, and historical product data through Kee…