Skip to main content
Glama
vatnode

vatnode

Official

vatnode-mcp

npm version Tests License: MIT vatnode/vatnode-mcp MCP server

Official Model Context Protocol server for vatnode — VAT validation and EU tax data for AI agents.

Lets AI assistants (Claude Desktop, Cursor, ChatGPT, Continue, Cline, …) look up VAT rates, check VAT number formats, and validate VAT IDs against the EU VIES service without leaving the chat.

  • Free, offline — VAT rates and format checks for 45 European countries, no account needed

  • Live validation — verify EU VAT numbers against VIES, get the registered company + audit-grade consultation number (requires a free vatnode API key; the consultation number is produced once you set your own VAT as requester in dashboard Settings)

  • Five focused tools — well-described for accurate agent tool selection

  • Pure stdio, zero hosted dependencies, runs locally via npx


Tools

Tool

Free

Description

get_country_vat_rates

Standard / reduced / super-reduced / parking rates + VAT number format for a country

list_eu_vat_rates

All 27 EU member states (plus XI for Northern Ireland) at once

check_vat_format

Offline syntactic check of a VAT number against the country regex

list_supported_countries

All 45 supported countries and which ones support full VIES validation

validate_vat_number

🔑

Live VIES validation — returns validity, company name, address, registration date, and (when a requester VAT is set in dashboard Settings) an audit-grade consultation number

Free tools work fully offline — data is bundled via eu-vat-rates-data and updated daily from the European Commission TEDB.

validate_vat_number requires a vatnode API key. The free tier includes a monthly request quota — get one in 30 seconds.


Related MCP server: Tax MCP Agent

Install

Claude Desktop

Add to your claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "vatnode": {
      "command": "npx",
      "args": ["-y", "vatnode-mcp"],
      "env": {
        "VATNODE_API_KEY": "vat_live_..."
      }
    }
  }
}

Restart Claude Desktop. The vatnode tools will appear in the tool picker.

You can omit VATNODE_API_KEY if you only need the free tools (rates, format checks).

Cursor

Settings → MCP → Add new server:

{
  "mcpServers": {
    "vatnode": {
      "command": "npx",
      "args": ["-y", "vatnode-mcp"],
      "env": { "VATNODE_API_KEY": "vat_live_..." }
    }
  }
}

ChatGPT (custom connectors / Apps SDK)

Configure as an stdio MCP server with the same npx -y vatnode-mcp command. See the Apps SDK docs.

Continue / Cline / other clients

Any MCP-compatible client can connect — point it at npx -y vatnode-mcp and (optionally) pass VATNODE_API_KEY via environment.


Get an API key

validate_vat_number requires a vatnode account. The platform also offers things the MCP doesn't expose:

  • Webhooks for VAT status changes (monitor a customer's VAT continuously)

  • Bulk validation

  • National-database fallback when VIES is down

  • VIES consultation numbers (audit-grade proof of validation)

  • Per-key rate limiting + dashboard analytics

Sign up free →


Example session

You: What's the VAT rate in Finland and Germany?

(Agent calls get_country_vat_rates for FI and DE — free, no key.)

Agent: Finland's standard VAT is 25.5%, Germany's is 19%. Finland has reduced rates of 14% and 10%; Germany has 7%.

You: Is IE6388047V a valid VAT?

(Agent calls validate_vat_number — requires API key.)

Agent: Yes, it's valid. Registered to GOOGLE IRELAND LIMITED at Gordon House, Barrow Street, Dublin 4.


Configuration

Env var

Required

Default

Purpose

VATNODE_API_KEY

for validate_vat_number

API key from https://vatnode.dev

VATNODE_API_URL

no

https://api.vatnode.dev

Override the API base (self-hosting / staging)


Contributing

Bug reports and PRs welcome. Open an issue first for non-trivial changes so we can align on direction.

git clone https://github.com/vatnode/vatnode-mcp.git
cd vatnode-mcp
npm install
npm test

Releasing

Releases are published to npm via Trusted Publishing — no NPM_TOKEN secret, every release signed with npm provenance.

# bump the version in ALL of: package.json, src/index.ts (VERSION),
# and server.json (top-level "version" + packages[0].version — the MCP
# Registry publish reads server.json and rejects a duplicate version).
# Commit, then:
git tag v0.3.2
git push --tags

CI on .github/workflows/release.yml picks up the tag and publishes.

License

MIT

Available Tools

5 tools
check_vat_formatCheck VAT number formatA

Performs an offline syntactic check of a VAT number against the country-specific regex pattern. Does NOT verify the VAT with VIES — use validate_vat_number for that. Use when the user wants a quick sanity check on the shape of a VAT ID without burning a quota call. Free, no API key required.

ParametersJSON Schema
NameRequiredDescriptionDefault
vatIdYesA VAT number, with or without spaces/dashes, with or without country prefix (e.g. "DE123456789", "IE 6388047 V").

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden. It discloses that the check is offline, syntactic only, does not verify with VIES, and is free with no API key required. However, it does not describe the return format (e.g., boolean or error), which would enhance transparency further.

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

Conciseness5/5

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

The description is two sentences, with the first sentence stating the core purpose, the second adding limitations and usage context. Every sentence is valuable, and the structure is front-loaded.

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

Completeness4/5

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

Given the tool has one parameter, no output schema, and no annotations, the description covers purpose, usage, and key behavioral traits well. It is missing explicit mention of the response, but for a simple check tool this is acceptable.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents the parameter well. The description does not add extra meaning beyond what is in the schema's parameter description. Baseline 3 is appropriate.

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 clearly states it performs an offline syntactic check of a VAT number against country-specific regex patterns, and explicitly distinguishes from the sibling tool validate_vat_number. The verb 'check' and resource 'VAT format' are specific and unambiguous.

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 explicitly says when to use (quick sanity check, free, no API key) and when not to use (if VIES verification is needed, use validate_vat_number). It provides clear context and an alternative tool.

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

get_country_vat_ratesGet VAT rates for a countryA

Returns the standard, reduced, super-reduced and parking VAT rates for a single European country, plus the VAT number format and regex. Accepts ISO 3166-1 alpha-2 codes (DE, FR, IT, …); also covers non-EU European jurisdictions where available (NO, CH, GB, UA, TR, …). Use when the user asks "what is the VAT rate in X" or needs the VAT number format for a country. Free, no API key required.

ParametersJSON Schema
NameRequiredDescriptionDefault
countryCodeYesISO 3166-1 alpha-2 country code, e.g. "DE", "FR", "IT".

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden. It discloses the tool is free and requires no API key, implying a read-only operation. It details the output content. It does not mention error handling or rate limits, but the level of detail is adequate for a simple tool.

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

Conciseness5/5

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

Three well-structured sentences. The first sentence lists what is returned, the second explains input format and coverage, and the third states usage trigger and free nature. No redundancy.

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

Completeness4/5

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

Given a simple tool with one parameter and no output schema, the description covers usage, input semantics, output content, and a behavioral note. Missing error handling or details on response format, but overall complete for typical agent invocation.

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% with a clear description of the parameter. The tool description adds context by specifying the set of valid countries (European jurisdictions) and the format expectations, going beyond the schema.

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 clearly states the tool returns standard, reduced, super-reduced, and parking VAT rates along with VAT number format and regex for a single European country. It specifies the input format (ISO 3166-1 alpha-2). It distinguishes from sibling tools by focusing on a single country's full rate set, unlike list_eu_vat_rates which likely lists all countries, or check_vat_format which checks format validity.

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

Usage Guidelines4/5

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

Explicitly says 'Use when the user asks "what is the VAT rate in X" or needs the VAT number format for a country.' It also notes coverage of non-EU European jurisdictions. While it doesn't explicitly list when not to use or alternatives, the guidance is sufficient for common use cases.

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

list_eu_vat_ratesList EU VAT ratesA

Returns current VAT rates for all EU member states (plus XI for Northern Ireland). Use when the user asks for an overview, a comparison across countries, or "all EU VAT rates". For a single country prefer get_country_vat_rates. Data is sourced from the EU Commission TEDB and updated daily. Free, no API key required.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.6/5.0
Behavior4/5

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

No annotations provided, so description carries full burden. It discloses data source (EU Commission TEDB), update frequency (daily), and that it's free with no API key required. However, it could explicitly state it's read-only and has no side effects.

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

Conciseness5/5

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

Three sentences: first states purpose, second provides usage guidance, third adds data source and constraints. No wasted words, front-loaded with most important information.

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

Completeness4/5

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

Given simple tool with no parameters and no output schema, description is nearly complete. It covers purpose, usage, source, update frequency, and cost. Minor gap: does not describe return format (e.g., map of country to rates), but output schema is absent so that expectation is low.

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?

Zero parameters, so description need not add parameter meaning. Schema coverage is 100% (empty). Baseline for 0 parameters is 4, and description correctly focuses on tool behavior without parameter clutter.

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?

Clearly states it returns current VAT rates for all EU member states plus Northern Ireland. Distinguishes from sibling get_country_vat_rates by noting preference for single country queries.

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?

Explicitly tells when to use (overview, comparison, 'all EU VAT rates') and when not to (single country, prefer get_country_vat_rates). Provides clear guidance on alternatives.

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

list_supported_countriesList supported countriesA

Returns the list of countries the vatnode MCP server has VAT data for. Distinguishes EU member states (eligible for full VIES validation) from other European jurisdictions (rate lookup only).

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.6/5.0
Behavior2/5

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

With no annotations, the description must disclose behavioral traits. It states the tool distinguishes EU from non-EU countries, which is helpful, but it does not clarify the output format (e.g., names, codes) or whether non-European countries are included. Missing details like response structure or potential limitations.

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

Conciseness5/5

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

The description is two concise sentences, front-loading the core purpose and adding a key distinction. Every sentence adds value without redundancy.

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

Completeness2/5

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

No output schema is provided, so the description must explain return values. It mentions a list of countries with a distinction between EU and non-EU, but it does not specify the exact format (e.g., ISO codes, names), whether non-European countries are included, or the structure of the response. This leaves ambiguity.

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?

The tool has no parameters and 100% schema coverage. The description does not need to add parameter info, so baseline score of 4 is appropriate.

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 clearly states that the tool returns a list of countries with VAT data from the vatnode MCP server, and it distinguishes between EU member states and other European jurisdictions. This is specific and differentiates the tool from siblings like list_eu_vat_rates.

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

Usage Guidelines3/5

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

The description implies usage when you need to know supported countries, but it does not explicitly state when to use this tool over siblings like get_country_vat_rates or check_vat_format. No when-not or alternative guidance is provided.

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

validate_vat_numberValidate EU VAT numberA

Verifies an EU VAT number against the official VIES service and returns validity, company name, address, registration date and other metadata. When the requester (your own VAT) is configured on the vatnode account, also returns a VIES consultation number — audit-grade proof of validation. Use whenever the user wants to confirm a VAT is real, look up the company behind a VAT, or needs evidence for accounting/compliance. Requires a vatnode API key (free tier available). Only EU-27 + XI (Northern Ireland) are supported by VIES.

ParametersJSON Schema
NameRequiredDescriptionDefault
vatIdYesEU VAT number, with country prefix. Spaces and dashes are stripped. Examples: "DE123456789", "IE6388047V", "FR12345678901".
requesterCountryCodeNoOptional: 2-letter country code of the party doing the check. Together with requesterVatNumber, asks VIES to issue an audit consultation number.
requesterVatNumberNoOptional: VAT number of the party doing the check. Pair with requesterCountryCode to get a consultation number.

TDQS

A5/5.0
Behavior5/5

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

Discloses that it connects to VIES, returns metadata, and optionally provides a consultation number for audit trails. No destructive behavior; API key requirement and country limitations are stated.

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

Conciseness5/5

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

Concise paragraph with clear flow: main purpose, special case, when to use, prerequisites and limitations. No redundant sentences.

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?

Fully describes output (validity, company info, registration date, consultation number) and constraints (EU-27+XI, API key). No output schema, so description carries complete burden.

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

Parameters5/5

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

Adds meaning beyond schema: explains requesterCountryCode/requesterVatNumber pair yields consultation number, and that vatId has spaces/dashes stripped. Schema coverage is 100% but description enriches it.

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 clearly states the tool verifies EU VAT numbers against VIES, listing specific returned data. It is distinct from siblings like check_vat_format (format only) and others (rates/lists).

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?

Explicitly states use cases: confirm VAT real, look up company, evidence for compliance. Also mentions API key requirement and supported countries, providing clear context for when to use.

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

TDQS

A4.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: syntactic check vs VIES validation, single-country vs all-EU rates, and supported countries list. No overlap.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (check_vat_format, get_country_vat_rates, list_eu_vat_rates, list_supported_countries, validate_vat_number) using snake_case.

Tool Count5/5

5 tools cover the essential VAT operations without being excessive or insufficient. The scope is well-defined for a VAT-specific MCP server.

Completeness5/5

The set covers all core VAT needs: syntactic validation, single and aggregate rate lookup, supported country listing, and VIES verification. No obvious gaps for typical use cases.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    F
    maintenance
    An MCP server for European invoicing rules. Query VAT rates, e-invoicing requirements, format specifications, and compliance rules for EU-27 + EEA countries.
    24
    MIT
  • F
    license
    A
    quality
    B
    maintenance
    MCP server for VAT/tax calculation based on country and price, supporting integration with LLM clients like Claude and Ollama for natural language queries.
    1
  • A
    license
    A
    quality
    B
    maintenance
    Local MCP server for validating EU VAT numbers using the official VIES API. Enables AI to check VAT validity and optionally retrieve consultation numbers for legal proof.
    2
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    MCP server for the Frankfurter exchange-rate API, enabling currency conversion and rate queries.
    2

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/vatnode/vatnode-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server