Skip to main content
Glama

VAT Validator MCP

by io.github.OjasKord

validate_vat

Validates a VAT number against live government registries. Call this BEFORE submitting any B2B payment via an agentic payment rail -- at the moment a VAT number appears on a supplier invoice and Stripe MPP, Alipay AI Pay, or Shopify UCP has not yet been called -- and BEFORE submitting any structured invoice under e-invoicing mandates now active or imminent: Belgium B2B (active Jan 2026), France B2B (Sep 2026), Poland KSeF (Feb 2026), AU GST digital reporting (ongoing). Use this when a supplier invoice carries a VAT number and your agent must confirm it is registered to the correct entity before approving payment or submitting a mandate-compliant e-invoice. Validates against EU VIES (ec.europa.eu, 27 member states) and AU ABR (abr.business.gov.au) live registries. Returns PROCEED / VERIFY_MANUALLY / HOLD verdict with fraud risk score 0-100 and name-match check. A settled B2B payment against an invalid or mismatched VAT number creates unrecoverable tax liability -- no agentic rail reverses a cleared cross-border transfer; an e-invoice submitted with an invalid VAT number is rejected at the mandate platform, halting the payables workflow. Pass the country_code from this response to get_vat_rates. One call, machine-ready verdict, no further analysis needed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vat_numberYesVAT number with country prefix. EU: DE123456789. AU: ABN12345678901.
invoice_amountNoInvoice amount in local currency — used in fraud risk weighting.
invoice_company_nameNoCompany name as it appears on the invoice — if provided, cross-checks against registry and flags mismatches.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
validYesWhether the VAT number is currently registered and active per the source registry
addressNo
summaryNo
checked_atYes
name_matchNo
source_urlYes
vat_numberYes
_disclaimerNo
agent_actionYesMachine-readable verdict
company_nameNo
jurisdictionYes
fraud_signalsNo
recommendationNo
fraud_risk_levelNo
fraud_risk_scoreNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • changedInput schema / properties / vat_number / description
      Previous value: -"VAT number with country prefix. EU: DE123456789. UK: GB123456789. AU: ABN12345678901."New value: +"VAT number with country prefix. EU: DE123456789. AU: ABN12345678901."
    • changedOutput schema / properties / jurisdiction / enum
      Previous value: -[
-  "UK",
-  "EU",
-  "AU"
-]New value: +[
+  "EU",
+  "AU"
+]
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "_disclaimer": {
+      "type": "string"
+    },
+    "address": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "agent_action": {
+      "description": "Machine-readable verdict",
+      "enum": [
+        "PROCEED",
+        "VERIFY_MANUALLY",
+        "HOLD"
+      ],
+      "type": "string"
+    },
+    "checked_at": {
+      "format": "date-time",
+      "type": "string"
+    },
+    "company_name": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "fraud_risk_level": {
+      "enum": [
+        "LOW",
+        "MEDIUM",
+        "HIGH",
+        "CRITICAL"
+      ],
+      "type": "string"
+    },
+    "fraud_risk_score": {
+      "maximum": 100,
+      "minimum": 0,
+      "type": "number"
+    },
+    "fraud_signals": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "jurisdiction": {
+      "enum": [
+        "UK",
+        "EU",
+        "AU"
+      ],
+      "type": "string"
+    },
+    "name_match": {
+      "enum": [
+        "MATCH",
+        "MISMATCH",
+        "NOT_CHECKED"
+      ],
+      "type": "string"
+    },
+    "recommendation": {
+      "enum": [
+        "CLEAR",
+        "REVIEW",
+        "BLOCK"
+      ],
+      "type": "string"
+    },
+    "source_url": {
+      "type": "string"
+    },
+    "summary": {
+      "type": "string"
+    },
+    "valid": {
+      "description": "Whether the VAT number is currently registered and active per the source registry",
+      "type": "boolean"
+    },
+    "vat_number": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "agent_action",
+    "valid",
+    "vat_number",
+    "jurisdiction",
+    "source_url",
+    "checked_at"
+  ],
+  "type": "object"
+}
  3. Changed3 schema fields changed
    • addedInput schema / properties / invoice_amount
      Added value: +{
+  "description": "Invoice amount in local currency — used in fraud risk weighting.",
+  "type": "number"
+}
    • addedInput schema / properties / invoice_company_name
      Added value: +{
+  "description": "Company name as it appears on the invoice — if provided, cross-checks against registry and flags mismatches.",
+  "type": "string"
+}
    • changedInput schema / properties / vat_number / description
      Previous value: -"VAT number with country prefix (e.g. DE123456789, GB123456789, FR12345678901)"New value: +"VAT number with country prefix. EU: DE123456789. UK: GB123456789. AU: ABN12345678901."
  4. First observed

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully discloses behavior: it validates against EU VIES and AU ABR live registries, returns a PROCEED/VERIFY_MANUALLY/HOLD verdict with fraud risk score and name-match check. It also reveals critical downstream consequences (unrecoverable tax liability for invalid VAT, rejection at mandate platforms) and states the tool is a one-call, machine-ready verdict, providing complete transparency about its operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and then expands into timing, registries, returns, and consequences. While it is longer than typical descriptions, the added length is justified by the compliance-critical context. There is minor redundancy between 'Call this BEFORE...' and 'Use this when...', but overall structure is logical and every section adds meaningful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no annotations, the description is highly complete: it covers the exact use case, timing, data sources, return format, risk implications, and integration with a sibling tool. For a tool with three parameters and an output schema (not shown), this description fully equips an agent to select and invoke the tool correctly, even without seeing the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the schema descriptions already explain invoice_amount and invoice_company_name. The description adds value by connecting the response (country_code) to the sibling tool get_vat_rates, and it mentions the fraud risk weighting indirectly, enriching the parameter context beyond the schema. This justifies a score slightly above the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Validates') and object ('VAT number against live government registries'), making the core function immediately clear. It also distinguishes itself from the sibling tool by explicitly referencing how to pass country_code to get_vat_rates, showing where this tool fits relative to alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit timing instructions ('Call this BEFORE submitting any B2B payment...') and describes the exact trigger ('when a supplier invoice carries a VAT number...'). It also names specific integration points (Stripe MPP, Alipay AI Pay, Shopify UCP) and explains the relationship to get_vat_rates, leaving no ambiguity about when to use this tool versus the sibling.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All VAT Validator MCP toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0
Disambiguation5/5

The two tools have completely distinct purposes: one retrieves VAT rates for a jurisdiction, the other validates a VAT number against live registries. There is no overlap, and the descriptions clearly cross-reference each other for the intended workflow.

Naming Consistency5/5

Both tool names follow the same verb_noun snake_case pattern: 'get_vat_rates' and 'validate_vat'. This is a predictable and consistent naming convention.

Tool Count4/5

With only two tools, the server is on the lean side, but the narrow domain of VAT validation and rate retrieval justifies a small surface. The purpose is specific, so two tools feel appropriate rather than insufficient.

Completeness4/5

The tools cover the core operations of a VAT-related MCP: validating VAT numbers and retrieving current rates. Minor gaps exist, such as no bulk validation or VAT amount calculation, but these are not critical for the server's stated purpose.

Resources