# org.scienceswarm/commerce-validators (remote · mcp.scienceswarm.org)

Commerce validators: live EU VAT (VIES), EORI, email/MX lookups; IBAN/ABA/GTIN checksums; VAT rates.

- Trust score: 57/100 (low)
- Change this week: +45
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.scienceswarm.org`: 57/100 (this document), [markdown](https://verifymcp.io/servers/org-scienceswarm-commerce-validators/mcp.md), [page](https://verifymcp.io/servers/org-scienceswarm-commerce-validators/mcp)

## Channel facts

- Endpoint: `https://mcp.scienceswarm.org/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.1`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 10 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 875 tokens (~87/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http org-scienceswarm-commerce-validators https://mcp.scienceswarm.org/mcp
```

### Codex

```toml
[mcp_servers.org-scienceswarm-commerce-validators]
url = "https://mcp.scienceswarm.org/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "org-scienceswarm-commerce-validators": {
      "type": "remote",
      "url": "https://mcp.scienceswarm.org/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add org-scienceswarm-commerce-validators --url https://mcp.scienceswarm.org/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  org-scienceswarm-commerce-validators:
    url: "https://mcp.scienceswarm.org/mcp"
```

### Other

```json
{
  "mcpServers": {
    "org-scienceswarm-commerce-validators": {
      "type": "http",
      "url": "https://mcp.scienceswarm.org/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 57, +39)

- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 10 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.27
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 18, +6)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 12, −42)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.07 → unverified
- [security regression] Transport: pass → fail
- [security] Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the tool list to see what that exposes.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-07-28 (score 54, +42)

- [security improvement] Transport: fail → pass
- [security] Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 10 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
- [functional improvement] Stability: unverified → 0.07
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-27 (score 12, −41)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 53)

First indexed and scored.

## MCP tools (10)

### `validate_iban` (~64 tokens)

Validate an IBAN (International Bank Account Number) by structure + the ISO 7064
mod-97 checksum. Catches typos/invalid accounts before you initiate a transfer.
Pure-algorithm; no data leaves the machine.

Input parameters:

- `iban` (string, required)

### `validate_gtin` (~60 tokens)

Validate a GTIN / UPC / EAN barcode (GTIN-8/12/13/14) by its check digit.
Catches mistyped product barcodes in inventory/catalog workflows. Pure-algorithm.

Input parameters:

- `code` (string, required)

### `validate_aba_routing` (~56 tokens)

Validate a US ABA bank routing number (9 digits) by its checksum. Catch typos
before initiating an ACH/wire payout. Pure-algorithm; nothing leaves the machine.

Input parameters:

- `routing_number` (string, required)

### `validate_eu_vat` (~111 tokens)

Validate an EU VAT number against the official EU VIES service (live government
lookup). Returns whether it is registered/valid and, if available, the registered
trader name + address. An LLM cannot know this without the real lookup — use this
before invoicing/reverse-charging an EU B2B customer. Input e.g. 'DE811569869' or
'IE6388047V' (country code + number).

Input parameters:

- `vat_number` (string, required)

### `validate_eori` (~88 tokens)

Validate an EORI number (Economic Operators Registration and Identification)
against the official EU customs database (live lookup). An EORI is required for
EU imports/exports — check a trading partner's or your own EORI before customs
filings / freight bookings. Input e.g. 'DE1234567890123' (country code + number).

Input parameters:

- `eori` (string, required)

### `check_email_domain` (~70 tokens)

Check whether a domain can actually receive email (has MX records) via a real
DNS-over-HTTPS lookup — validate a customer/supplier email's domain before sending
or invoicing. An LLM can't know current DNS; this does the live lookup.

Input parameters:

- `email_or_domain` (string, required)

### `vat_rate_by_country` (~110 tokens)

EU VAT rates (standard / reduced / super-reduced / parking) for a country,
from the maintained ibericode/vat-rates dataset (fetched live, cached 24h) —
including which rate set was in force on an optional 'date' (YYYY-MM-DD) and the
names of regional exceptions (e.g. Canary Islands). Input e.g. 'DE', 'FR', 'HU'.

Input parameters:

- `country_code` (string, required)
- `date` (string)

### `stripe_connect_split` (~152 tokens)

Compute the Stripe Connect three-way split for one charge.

Returns what the buyer pays, what Stripe takes, what the platform nets (its
application fee), and what the connected seller nets — plus the platform's
effective take rate. fee_bearer: 'seller' | 'platform' | 'buyer' (who absorbs the
Stripe processing fee). Rates are editable; defaults are US card standard 2.9%+$0.30.

Input parameters:

- `application_fee_fixed` (number)
- `application_fee_pct` (number)
- `charge_amount` (number, required)
- `fee_bearer` (string)
- `processing_fixed` (number)
- `processing_pct` (number)

### `payout_reconciliation` (~94 tokens)

Explain why a payout is less than sales: walk gross -> deductions -> expected,
and (if actual_deposit given) flag the unexplained gap (shortfall/surplus).

Input parameters:

- `actual_deposit`
- `chargebacks` (number)
- `gross_sales` (number, required)
- `other_deductions` (number)
- `processing_fees` (number)
- `refunds` (number)

### `reorder_point` (~70 tokens)

Reorder point = lead-time demand + safety stock. If on_hand is given, returns
whether to reorder now and the days of cover remaining.

Input parameters:

- `avg_daily_sales` (number, required)
- `lead_time_days` (number, required)
- `on_hand`
- `safety_stock` (number)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/org-scienceswarm-commerce-validators/mcp#diagnostics

## Score history

- 2026-08-03: 57
- 2026-08-02: 18
- 2026-08-01: 18
- 2026-07-31: 18
- 2026-07-30: 12
- 2026-07-29: 12
- 2026-07-28: 54
- 2026-07-27: 12
- 2026-07-26: 53

## Links

- Remote endpoint: https://mcp.scienceswarm.org/mcp
- Repository: https://github.com/vajdap/commerce-validators-mcp
- Changelog RSS feed: https://verifymcp.io/servers/org-scienceswarm-commerce-validators/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/org-scienceswarm-commerce-validators/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/org-scienceswarm-commerce-validators/mcp