Ha Tang docs and API for agents: email, VietQR payments, e-invoices, support inbox (Vietnam).
Nothing to run from here
RevClamp is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
9
tools declared
local
or remote
—
downloads a day
What it does
Zero-take-rate Stripe 2025-03-31.basil, Visa CE 3.0 & EU/XI VIES VAT guardrails MCP server.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user revclamp-mcp-2 '--' npx -y revclamp-mcp
# 2 — ask your agent for something these tools do
# revclamp_audit_revenue_leakage, revclamp_evaluate_ghost_usage, revclamp_stage_stripe_dispute_ce3 and 6 more
RevClamp costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
REAll 2 servers
revclamp2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user revclamp-mcp-2 '--' npx -y revclamp-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Or connect to its publisher’s address
Its publisher also runs it at https://revclamp.com/api/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http revclamp-mcp-2 https://revclamp.com/api/mcpFree on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
9 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Run a deterministic 90-day B2B revenue leakage and chargeback readiness audit across Stripe subscriptions, AI/API usage telemetry events, and open disputes. Executes as a 100% read-only, stateless diagnostic with zero external Stripe mutations. Returns structuredContent containing ok, mode, statelessEphemeralAudit, tenantId, dunningGracePeriodDays, costPerEventCents, and audit (scannedCustomers, s
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dunningGracePeriodDays | integer | no | Custom dunning grace window in integer days (valid range: 0 to 14, default: 3) allowed after latest_invoice_failed_at before flagging past_due subscriptions as unpaid ghost usage. |
| costPerEventCents | integer | no | Estimated marginal compute or API cost per leaked usage event in integer USD cents (valid range: 1 to 100000, default: 142 i.e. $1.42/event). |
| customers | array | no | Optional array of up to 50 Stripe customer snapshots (each with id like 'cus_123', optional email, subscriptions array or list object, and subscriptionsHasMore: false). Omit to run against workspace t |
| usageEvents | array | no | Optional array of up to 200 product/AI API usage telemetry events (each with stripe_customer_id or email, event_name, and occurredAtSec Unix timestamp in seconds). |
| disputes | array | no | Optional array of up to 50 Stripe dispute objects (each with id like 'du_123', customer, amount in cents, reason such as 'fraudulent', and status such as 'needs_response'). |
| demo | boolean | no | Optional simulation flag (boolean) for deterministic sample audit preview. |
Evaluate whether a specific customer's AI or API usage event constitutes unpaid ghost usage across multi-subscription Stripe 2025-03-31.basil state, enforcing fail-closed pagination (has_more must be explicitly false) and configurable 0-14 day dunning grace windows. Executes as a stateless, read-only entitlement evaluator with zero side effects. Returns structuredContent containing ok, mode, state
| Parameter | Type | Required | Notes |
|---|---|---|---|
| customerId | string | no | Stripe customer identifier to evaluate (format example: 'cus_9s6XKzkNRiz8i3', max 64 chars). |
| subscriptions | yes | Required Stripe customer subscriptions payload: either a Stripe list object ({ data: [...], has_more: false }) or a raw array of up to 50 subscription objects containing id, status ('active', 'trialin | |
| usageEvent | object | no | Optional metered usage event object containing customer_id (or stripe_customer_id), event_name, and occurred_at (or occurred_at_sec). |
| subscriptionsHasMore | boolean | no | Pagination completeness flag (boolean). Must be explicitly set to false when passing a raw subscriptions array so RevClamp can verify no active subscription was truncated on a later page. |
| dunningGracePeriodDays | integer | no | Dunning grace window in integer days (valid range: 0 to 14, default: 3) after latest_invoice_failed_at during which past_due subscriptions remain entitled. |
| usageTimestampSec | integer | no | Optional Unix epoch timestamp in integer seconds (e.g. 1761264000) when the AI/API usage event occurred (defaults to current server Unix timestamp if omitted). |
| occurredAtSec | integer | no | Optional alias for usageTimestampSec: Unix epoch timestamp in integer seconds (e.g. 1761264000) when the usage event occurred (used when usageTimestampSec is omitted). |
| demo | boolean | no | Optional simulation flag (boolean) for deterministic ghost-usage preview. |
Evaluate Visa Compelling Evidence 3.0 (CE 3.0) qualification across 120-to-365-day historical charges (requiring at least 2 settled, non-refunded, non-disputed prior transactions sharing IP address, device fingerprint, or billing email) and assemble a non-destructive Stripe dispute evidence draft with submit hardcoded to false. Executes as a pure read-only staging computation that never auto-submi
| Parameter | Type | Required | Notes |
|---|---|---|---|
| disputeId | string | no | Stripe dispute identifier being staged (format example: 'du_1QxyzEnterpriseDispute01', default: 'du_mcp_staged_01', max 64 chars). |
| customerId | string | no | Stripe customer identifier associated with the disputed charge (format example: 'cus_enterprise_88', default: 'cus_mcp_enterprise_01', max 64 chars). |
| disputeReason | string | no | Stripe dispute reason code (e.g. 'fraudulent', 'unrecognized', 'subscription_canceled', 'product_unacceptable', 'general'; default: 'fraudulent'; Visa CE 3.0 applies to 'fraudulent' disputes). |
| existingUncategorizedText | string | no | Optional existing merchant evidence notes in Stripe evidence.uncategorized_text or access_activity_log (up to 18,000 chars) to preserve via append-only merge without overwriting. |
| existingAccessActivityLog | string | no | Optional alias for existingUncategorizedText: existing merchant evidence notes in Stripe evidence.access_activity_log (up to 18,000 chars) to preserve via append-only merge. |
| disputedTransaction | object | no | Optional disputed charge snapshot object containing id (e.g. 'ch_disputed_01'), occurredAtSec (Unix seconds), customer_id, email, ip_address, and device_id. |
| priorTransactions | array | no | Optional array of up to 1000 historical Stripe charge objects (each with id, status: 'succeeded', disputed: false, refunded: false, occurredAtSec 120-365 days prior to disputedTransaction, email, ip_a |
| usageEvents | array | no | Optional array of up to 200 customer product/API usage telemetry events (each with occurredAtSec Unix seconds, stripe_customer_id, and event_name) for append-only access_activity_log staging. |
| demo | boolean | no | Optional simulation flag (boolean) to stage a labeled sample dispute preview. |
Normalize EU-27 and Northern Ireland (XI) B2B VAT identifiers (including mandatory Greece ISO-3166 GR to EL prefix normalization) and evaluate cross-border 0% VAT reverse-charge eligibility, VIES consultation evidence, or MS_UNAVAILABLE circuit-breaker fulfillment hold actions. Read-only and non-destructive; supports deterministic simulation modes ('VALID', 'INVALID', 'MS_UNAVAILABLE') or real-tim
| Parameter | Type | Required | Notes |
|---|---|---|---|
| sellerCountry | string | no | Two-letter EU-27 or XI member state prefix of the merchant's dispatch warehouse (e.g. 'DE', 'NL', 'FR', 'EL', 'XI'; 'GR' is automatically normalized to 'EL'; default: 'DE'). |
| buyerVatId | string | yes | Required buyer EU or Northern Ireland VAT registration number to normalize and validate (e.g. 'DE123456789', 'GR123456789', 'NL123456789B01', 'XI123456789', max 40 chars). |
| viesMode | string | no | VIES evaluation mode: 'FORMAT_ONLY' (deterministic EU/XI syntax validation without consultation), 'VALID' (deterministic active VAT simulation, default), 'INVALID' (deterministic rejected VAT simulati |
| consultationNumber | string | no | Optional VIES requester consultation reference number (e.g. 'WAPIAAAAW998877', max 64 chars) to attach to deterministic 'VALID' mode tax audit records. |
| demo | boolean | no | Optional simulation flag (boolean) for deterministic VIES gateway preset evaluation. |
Reconcile B2B wholesale Net-15, Net-30, and Net-60 invoice deposits, partial payments, and credit notes using exact integer minor-unit (EUR/USD cent) arithmetic with zero IEEE-754 floating-point drift. Executes as a pure, stateless, read-only financial reconciliation function. Returns structuredContent containing ok, mode, statelessEphemeralAudit, tenantId, and reconciliation (state, status, fulfi
| Parameter | Type | Required | Notes |
|---|---|---|---|
| orderId | string | no | B2B wholesale order or invoice identifier (e.g. 'gid://shopify/Order/908812' or 'ORD-2026-9088', default: 'ord_local_b2b_01', max 64 chars). |
| totalOrderCents | integer | no | Gross invoice total in positive integer minor currency units / cents (e.g. 250000 for 2,500.00 EUR; must be > 0). |
| orderTotalCents | integer | no | Alias for totalOrderCents: gross invoice total in positive integer minor currency units / cents (must be > 0). |
| paidAmountCents | integer | yes | Required cumulative amount collected from the buyer in non-negative integer cents (e.g. 75000 for 750.00 EUR; must be >= 0). |
| creditNoteCents | integer | no | Optional post-invoice credit notes or return adjustments in integer cents (valid range: 0 to totalOrderCents, default: 0; singular alias for creditNotesCents). |
| creditNotesCents | integer | no | Optional post-invoice credit notes or return adjustments in integer cents (valid range: 0 to totalOrderCents, default: 0; plural alias for creditNoteCents). |
| requiredDepositCents | integer | no | Optional explicit upfront deposit threshold in integer cents (valid range: 0 to effectiveTotalCents). Overrides requiredDepositPercent when provided. |
| requiredDepositPercent | integer | no | Optional upfront deposit percentage required before releasing warehouse fulfillment hold (valid range: 0 to 100, default: 30 i.e. 30% upfront deposit). |
| paymentTermsDays | integer | no | Optional B2B net payment terms maturity window in integer days (allowed values: 15, 30, or 60 for Net-15, Net-30, or Net-60; default: 30). |
| daysElapsedSinceInvoice | integer | no | Optional elapsed integer days since invoice issuance (valid range: 0 to 3650, default: 5). |
| toleranceCents | integer | no | Optional rounding/FX reconciliation tolerance in integer cents (valid range: 0 to min(500, 1% of totalOrderCents), default: 0). |
| demo | boolean | no | Optional sandbox flag (boolean). |
Generate and verify canonical Stripe-Signature (t=<unix>,v1=<hex_sha256>), X-Shopify-Hmac-Sha256 (<base64_sha256>), and X-RevClamp-Signature (t=<unix>,v1=<hex_sha256>) headers over exact UTF-8 webhook payload bytes using crypto.timingSafeEqual and a 300-second replay window guard. Enforces a Zero-Trust guard that blocks known live/production credential patterns (sk_live_, rk_live_, non-test whsec_
| Parameter | Type | Required | Notes |
|---|---|---|---|
| provider | string | no | Webhook signature provider scheme to evaluate: 'stripe' (Stripe-Signature t=<sec>,v1=<hex>, default), 'shopify' (X-Shopify-Hmac-Sha256 Base64 raw UTF-8 HMAC), or 'revclamp' (X-RevClamp-Signature t=<se |
| secret | string | no | Synthetic or test webhook signing secret (default: 'whsec_test_revclamp_sandbox_secret_2026', max 256 chars, or comma-separated rotation secrets). Live production secrets (sk_live_, rk_live_, non-test |
| secrets | array | no | Optional array of 1 to 5 synthetic/test webhook signing secrets (each <= 256 chars) to evaluate during rolling webhook secret rotation. |
| rawPayload | string | no | Exact unparsed UTF-8 webhook request body string (up to 16,384 chars) used to compute the canonical SHA-256 HMAC digest. Defaults to a provider-specific sample JSON event if omitted. |
| timestampSec | integer | no | Optional Unix epoch timestamp in integer seconds (valid range: 1 to 9999999999; defaults to current server Unix timestamp) used when generating or verifying timestamped Stripe/RevClamp headers. |
| signatureHeader | string | no | Optional supplied HTTP signature header value to verify via crypto.timingSafeEqual (e.g. 't=1760000000,v1=...' or Base64 digest, max 512 chars). Omit to run in GENERATE_AND_SELF_VERIFY mode. |
| toleranceSec | integer | no | Optional replay window tolerance in integer seconds (valid range: 1 to 3600, default: 300). |
| demo | boolean | no | Optional sandbox flag; uses synthetic defaults when provider, secret, or rawPayload are omitted. |
Deterministically calculate monthly and annual B2B margin savings using exact integer USD cents when replacing a 25%-30% contingency chargeback agency with RevClamp flat-rate 0% commission plans ($19 Starter, $59 Growth, $199 Scale). Evaluates monthlyWonDisputeUsd, monthlyGhostBleedUsd, contingencyTakeRatePercent, and monthlyUsageEvents to recommend the optimal tier. Returns structuredContent cont
| Parameter | Type | Required | Notes |
|---|---|---|---|
| monthlyWonDisputeUsd | number | no | Monthly won Stripe chargeback volume in USD (valid range: 0 to 10000000, default: 10000) subject to legacy agency take-rate fees. |
| monthlyGhostBleedUsd | number | no | Monthly unpaid AI/API or SaaS usage bleed stopped by RevClamp basil entitlement guards in USD (valid range: 0 to 10000000, default: 600). |
| contingencyTakeRatePercent | number | no | Competitor chargeback agency contingency commission percentage (valid range: 1 to 50, default: 25 for 25% take-rate tools). |
| monthlyUsageEvents | integer | no | Monthly verified usage events across your workspace (integer 0 to 50000000, default: 250000) used to recommend Starter (<=100k), Growth (<=1M), or Scale (<=5M). |
Deterministically evaluate an ordered or out-of-order sequence of 1-10 Stripe/Shopify/RevClamp subscription lifecycle webhooks against a 72-hour idempotency deduplication Set (eventId), a configurable idempotencyWindowSec (60s-2592000s, default: 259200s / 72h), and a monotonic transition timestamp guard (event.createdSec >= lastAppliedCreatedSec). Compares RevClamp's monotonic FSM against a naive
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scenarioPreset | string | no | Scenario preset to evaluate when custom events are omitted (default: 'out_of_order_stale_update_after_cancel'). |
| events | array | no | Optional custom array of 1 to 10 webhook events ({ eventId, eventType, createdSec, subscriptionStatus, tier, currentPeriodEndSec }) in arrival order. |
| nowSec | integer | no | Reference evaluation timestamp in Unix seconds used to check the 72-hour idempotency window. |
| idempotencyWindowSec | integer | no | Deduplication and replay-acceptance window in seconds (valid range: 60 to 2592000, default: 259200 for 72 hours). |
| demo | boolean | no | Optional sandbox flag to run the preset replay simulation. |
Deterministically lint a Stripe dispute evidence[access_activity_log] payload against Stripe's 18,000 UTF-16 code unit (String.prototype.length) ceiling, UTF-8 byte length, non-destructive --- BEGIN REVCLAMP CE3 EVIDENCE --- / --- END REVCLAMP CE3 EVIDENCE --- (or [RevClamp Verified Product Usage Log] / [/RevClamp Verified Product Usage Log]) delimiter markers, existing merchant note preservation,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| preset | string | no | Scenario preset to evaluate when custom evidenceLogText / accessActivityLog is omitted (default: 'valid_ce3_non_destructive'). |
| existingMerchantNotes | string | no | Existing human AE/support notes inside evidence[access_activity_log] that must be preserved. |
| evidenceLogText | string | no | Merged or candidate Stripe dispute evidence[access_activity_log] payload evaluated against the 18,000 UTF-16 code unit ceiling and non-destructive delimiter markers. |
| accessActivityLog | string | no | Alias for evidenceLogText representing Stripe dispute evidence[access_activity_log] payload. |
| priorMatchedCount | integer | no | Number of prior undisputed Stripe charges (120d-365d old) with matching customer_id and IP/device fingerprint (Visa CE 3.0 requires >= 2). |
| hasIpMatch | boolean | no | Whether the disputed charge IPv4/IPv6 address matches the historical undisputed charges. |
| hasDeviceMatch | boolean | no | Whether the disputed charge device_id fingerprint matches the historical undisputed charges. |
| disputedTransaction | object | no | Optional disputed Stripe charge/transaction metadata evaluated against priorTransactions for Visa CE 3.0 qualification. |
| priorTransactions | array | no | Optional historical undisputed Stripe charges (120d-365d prior) evaluated for Visa CE 3.0 two-identifier overlap. |
| demo | boolean | no | Set true to lint a sample preset fixture when evidenceLogText / accessActivityLog is omitted. |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install RevClamp or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 1.20.20 · scanned 5 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digestef3f33d9d40a70712d49539f5e11f5fb9dc4524bc7e5fe389ee679c8e77cb32a
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (9 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| revclamp_audit_revenue_leakage | no tags | |
| revclamp_evaluate_ghost_usage | no tags | |
| revclamp_stage_stripe_dispute_ce3 | no tags | |
| revclamp_validate_eu_vat_vies | no tags | |
| revclamp_reconcile_b2b_net_terms | no tags | |
| revclamp_verify_webhook_signature | external-sink | external-sink: keyword "webhook" |
| revclamp_calculate_roi_and_plan_fit | no tags | |
| revclamp_simulate_webhook_replay | external-sink | external-sink: keyword "webhook" |
| revclamp_lint_dispute_evidence | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestef3f33d9d40a7071
Scanned2026-11-05
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.20.20. Pin a release below and the command asks for exactly that one.
1.20.20
5 Nov 2026
latestNo release note was published with this version.
1.20.19
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish RevClamp can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.