This server only exposes a no-op diagnostic stub for an archived sandbox workspace.
Call legacy_sandbox_noop with an empty object ({}) to run a diagnostic/no-op.
The schema allows no input properties and rejects additional properties.
No actual RevClamp B2B, Stripe, VAT, webhook, dispute, or ROI tools are available in the provided server schema, despite the README.
Provides tools for auditing Stripe Billing and usage data, evaluating multi-subscription customer snapshots and dunning grace periods, and assessing/staging Stripe dispute evidence aligned with Visa CE 3.0 readiness.
Provides Visa CE 3.0 dispute-readiness capabilities, including evaluating prior undisputed charges and staging a non-submitting draft for dispute evidence review.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@deprecated-legacy-sandbox validate EU VAT ID GR123456789 in VIES"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
revclamp-mcp)
revclamp-mcp is a standalone, zero-dependency Open-Source Model Context Protocol (MCP) Server & CLI (index.mjs + local_engine.mjs) implementing 9 deterministic B2B FinOps, Stripe 2025-03-31.basil, Visa CE 3.0, EU/XI VIES VAT, Shopify Plus B2B Net-15/30/60, and Webhook Security tools in pure Node.js.
100% Local In-Process Execution (Default — Zero Network / Zero API Key Required): All 9 MCP tools (initialize, tools/list, and tools/call) execute locally in-process inside local_engine.mjs using pure Node.js (node:crypto HMAC-SHA256 verification, integer-cent double-entry accounting, 72-hour webhook replay state machines, and 18,000 UTF-16 code unit CE 3.0 linting). Zero network calls are ever made unless REVCLAMP_API_KEY or REVCLAMP_MCP_URL is explicitly configured.
Optional Hosted Cloud Workspace Sync (REVCLAMP_API_KEY): When REVCLAMP_API_KEY (rg_live_...) is configured, revclamp-mcp connects to RevClamp Enterprise (https://api.revclamp.com/api/mcp) to unlock the 90-day durable transactional usage & audit ledger, 24/7 autonomous Stripe dispute & entitlement webhook outbox, and real-time EU Commission VIES SOAP gateway consultation numbers.
local_engine.mjs) vs. Hosted Cloud (REVCLAMP_API_KEY)Capability | Local Open-Core Default (Zero API Key) | Hosted Cloud ( |
Execution & Network | 100% in-process ( | HTTPS JSON-RPC to |
Usage & Audit Storage | Stateless evaluation of caller-supplied JSON snapshots | Persistent 90-day durable transactional ledger + Stripe historical backfill |
Dispute & Entitlement Action | Returns non-destructive | 24/7 autonomous Stripe webhook outbox ( |
EU & | Deterministic syntax & | Live EU Commission VIES SOAP consultation IDs + circuit-breaker retry queue ( |
Monthly Event Tiers | Unlimited local in-process evaluations (0 network cost) | Free Sandbox ( |
Data Minimization & Privacy | Nothing ever leaves your machine | Only explicit |
Related MCP server: week7-mcp-server
local_engine.mjs (9)Tool Name | Domain | Local In-Process Implementation ( | Execution Mode |
| Stripe Billing & Usage | Evaluates caller-supplied customer/usage arrays ( | Local In-Process (or Optional Cloud Key) |
| Stripe | Evaluates multi-subscription customer snapshots ( | Local In-Process (or Optional Cloud Key) |
| Visa 10.4 / CE 3.0 | Evaluates 120d–365d prior undisputed charges ( | Local In-Process (or Optional Cloud Key) |
| EU & | Normalizes 27 EU member states + Northern Ireland ( | Local In-Process (or Optional Live VIES) |
| B2B Wholesale Net-30 | Reconciles Net-15/30/60 upfront deposits and credit notes using integer EUR-cent double-entry accounting | Local In-Process (or Optional Cloud Key) |
| Webhook HMAC-SHA256 | Generates and verifies | Local In-Process (or Optional Cloud Key) |
| 0% Take-Rate ROI & Plan Fit | Calculates monthly and annual B2B margin savings in integer USD cents vs. 25%–30% chargeback agencies and recommends the optimal tier | Local In-Process (or Optional Cloud Key) |
| Webhook Replay & FSM | Simulates subscription lifecycle webhooks against a 72h deduplication | Local In-Process (or Optional Cloud Key) |
| Dispute Evidence UTF-16 & CE 3.0 | Lints | Local In-Process (or Optional Cloud Key) |
Add revclamp-mcp to your claude_desktop_config.json or .cursor/mcp.json. By default, revclamp-mcp runs 100% locally in-process with zero network calls and zero API keys required:
{
"mcpServers": {
"revclamp": {
"command": "npx",
"args": ["-y", "github:lhphong09t2/revclamp-mcp"]
}
}
}(Optional) To connect to a live workspace on https://revclamp.com/dashboard, pass REVCLAMP_API_KEY in env or use the hosted Streamable HTTP endpoint (POST https://api.revclamp.com/api/mcp):
curl -sS -X POST https://api.revclamp.com/api/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'<60s Local Smoke Check (--self-test)# Run a <60s local CLI smoke check (verifies all 9 tool schemas & executes a local_engine.mjs sample audit with zero API key)
npx -y github:lhphong09t2/revclamp-mcp#v1.20.19 --self-test
# Provision a free Cloud Workspace instantly (zero email required; saves to ~/.revclamp/credentials.json) or bind a work email via 6-digit OTP
npx -y revclamp-mcp@1.20.19 --init-workspace
npx -y revclamp-mcp@1.20.19 --init-workspace you@company.com
# Verify the 6-digit OTP using REVCLAMP_API_KEY from environment
REVCLAMP_API_KEY="rg_live_..." npx -y revclamp-mcp@1.20.19 --verify-otp you@company.com 123456
# List all 9 MCP tools and JSON schemas (runs locally in-process)
node index.mjs --list-tools
# Validate an EU or Northern Ireland (XI) B2B VAT ID (auto-converts Greece GR -> EL)
node index.mjs --check-vat GR123456789 DE
# Calculate 0% take-rate ROI and optimal flat-rate plan fit (runs locally in-process)
node index.mjs --calc-roi 10000 600 25 250000
# Simulate out-of-order webhook replay and 72-hour deduplication state machine (runs locally)
node index.mjs --sim-replay out_of_order_stale_update_after_cancel
# Lint Stripe dispute evidence UTF-16 code units and non-destructive CE 3.0 markers (runs locally)
node index.mjs --lint-evidence valid_ce3_non_destructive
# Verify webhook HMAC-SHA256 using REVCLAMP_WEBHOOK_SECRET from environment (runs locally)
REVCLAMP_WEBHOOK_SECRET="whsec_test_secret_revclamp_sandbox_2026" node index.mjs --verify-webhook stripe
# Invoke Visa CE 3.0 readiness staging locally (pass demo: true for synthetic sample or usageEvents for real logs)
node index.mjs --call revclamp_stage_stripe_dispute_ce3 '{"disputeId":"du_1Qxyz01","customerId":"cus_ent_88","disputeReason":"fraudulent","demo":true}'2025-03-31.basil Entitlement Guard & Visa CE 3.0 Two-Tier Routing
Engineering Post-Mortem #1: Stripe's basil API broke my grace-period logic, and CE 3.0 turned out to be a routing problem
Engineering Post-Mortem #7: Visa CE 3.0 18,000 UTF-16 Code Unit Evidence Truncation & Non-Destructive Staging
Interactive Tools (No Signup):
HTTP 200 OK Soft-Failure Circuit Breaker & B2B Net-Terms Reconciliation
Engineering Post-Mortem #2: VIES returns HTTP 200 when it's down, and I charged the wrong VAT because of it
Engineering Post-Mortem #3: Shopify Plus B2B Net-15/30/60 Integer-Cent Deposit & Credit-Note Reconciliation
Interactive Tools (No Signup):
Engineering Post-Mortem #4: Why Stripe and Shopify Webhook HMAC-SHA256 Verification Fails on Parsed JSON Bodies
Engineering Post-Mortem #5: Chargeback Contingency Fees (25%–30%) vs. Flat-Rate 0% Commission Automation
Engineering Post-Mortem #6: Webhook Idempotency & Out-of-Order Subscription State Machines
Interactive Tools (No Signup):
Local-First Deterministic Execution: Runs all 9 tools locally in-process inside local_engine.mjs with zero external npm dependencies.
Strict Origin Pinning (Cloud Mode): When REVCLAMP_API_KEY is provided, only connects to https://api.revclamp.com/api/mcp or https://revclamp.com/api/mcp over TLS (redirect: "error").
Bounded Execution: Enforces a hard 10,000ms request timeout (AbortSignal.timeout) and a 32,768-byte request/response payload cap.
Full LLM Reference: https://revclamp.com/llms-full.txt
MIT © RevClamp Enterprise
No-op diagnostic stub for archived sandbox workspace.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and "no-op" is a genuinely valuable disclosure: the agent learns the call has no side effects. Beyond that it is silent — whether the call always succeeds, errors on archived workspaces, or is itself deprecated is left unstated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single short sentence with the most important fact (no-op) front-loaded and no waste. It could arguably use one more clause clarifying the diagnostic intent, but there is no padding to trim.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter, no-output tool the bar is low, and the description covers the essentials of what happens (nothing). It still leaves the agent unable to decide whether calling it is meaningful, which matters for a stub that may exist only for backward compatibility.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters and the schema is closed with additionalProperties=false, so there is nothing for the description to disambiguate. The baseline of 4 applies: no parameter semantics are needed here.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
"No-op diagnostic stub" identifies the resource as a placeholder and explicitly states it performs no action, which is useful. However, "diagnostic" for an "archived sandbox workspace" is never explained — the agent cannot tell what is being diagnosed or verified, so the purpose stays vague beyond the no-op label.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no indication of when this tool should be called, when it should not, or what alternative exists if any. The word "diagnostic" weakly implies a health-check use case, but nothing confirms it or tells the agent whether the tool is deprecated and should be avoided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.1legacy_sandbox_nooprevclamp_audit_revenue_leakagerevclamp_evaluate_ghost_usagerevclamp_reconcile_b2b_net_termsrevclamp_stage_stripe_dispute_ce3revclamp_validate_eu_vat_viesv1.0.0revclamp_audit_revenue_leakagerevclamp_evaluate_ghost_usagerevclamp_reconcile_b2b_net_termsrevclamp_stage_stripe_dispute_ce3revclamp_validate_eu_vat_viesScored across 1 tool
There is only one tool, so there is no possibility of selecting the wrong tool or confusing overlapping purposes. Its no-op diagnostic role is clearly distinguishable by default.
The single tool name uses a clear snake_case pattern and is descriptive of its legacy sandbox no-op behavior. There is no mixed convention to penalize.
A single trivial no-op tool is an extremely thin tool surface for an MCP server, even one framed as deprecated. The rubric treats a single trivial tool as an extreme mismatch.
The surface offers no meaningful lifecycle operations such as listing, inspecting, updating, or cleaning up sandbox workspaces. For the stated archived sandbox domain, a no-op diagnostic stub is severely incomplete.
A paid remote MCP for CLI tool MCP, built to return verdicts, receipts, usage logs, and audit-ready
A paid remote MCP for Skybridge, built to return verdicts, receipts, usage logs, and audit-ready JSO
A paid remote MCP for hosted MCP server, built to return verdicts, receipts, usage logs, and audit-r
Remote MCP utilities for agents: structured data, commerce checks, and x402 paid API discovery.
