Greece Invoices (AADE myDATA national API)
Server Details
Greece myDATA invoices for AI agents: build AADE XML, transmit to myDATA, query by MARK.
- Status
- Unhealthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.5/5 across 2 of 2 tools scored.
The two tools have completely distinct purposes: one creates invoices and the other queries by MARK. No ambiguity or overlap.
Both tool names follow a clear verb_noun pattern (create_invoice, query_invoice), consistent and predictable.
With only 2 tools, the server feels extremely thin for the scope of a national invoicing API. Essential operations like update, cancel, list, and search are missing.
The surface covers creation and query by MARK only, leaving major gaps such as updating, cancelling, listing invoices by criteria, or handling other document types.
Available Tools
2 toolscreate_invoiceAInspect
Issue a Greek electronic invoice (τιμολόγιο) into the national AADE myDATA platform. Builds an AadeBookInvoiceType XML and transmits it to /SendInvoices under your own AADE credentials, returning the official MARK (Μοναδικός Αριθμός Καταχώρησης / unique registration number), invoice UID and QR url. Bring your own credentials as headers: x-aade-user-id (your myDATA user id) and x-aade-subscription-key (your Ocp-Apim subscription key) — both issued by the AADE myDATA portal. Header x-aade-mode: prod switches to the live rail (default = dev / test rail, no fiscal effect). Amounts are in EUR, VAT-exclusive per line. Greek VAT rates map to AADE vatCategory codes automatically: 24 (mainland standard), 13 and 6 (reduced), 17 / 9 / 4 (island reduced), 0 (VAT-exempt, category 7). invoiceType defaults to 1.1 (sales invoice); use 2.1 for a services invoice or 5.1 for a credit note.
| Name | Required | Description | Default |
|---|---|---|---|
| aa | No | Invoice running number (Α/Α) within the series. Auto-generated if omitted. | |
| lines | Yes | Invoice lines. Each: net_value (line net total, VAT-exclusive EUR), vat_rate (24|13|9|6|4|17|0). Optional: description, vat_exemption_category (1-31, required by AADE when vat_rate is 0), income_classification_type + income_classification_category (E3/VAT classification if your accounting requires it). | |
| series | No | Invoice series (σειρά). Default "A". | |
| currency | No | Currency code. Default EUR. | |
| issue_date | No | Issue date (ημερομηνία έκδοσης), YYYY-MM-DD. Default: today (UTC). | |
| issuer_vat | No | Your (issuer/seller) Greek VAT number / ΑΦΜ, 9 digits (EL/GR prefix optional). Recommended; must match the credentials used. | |
| invoice_type | No | AADE invoiceType code. Default 1.1 (sales invoice). Common: 1.1 sales, 2.1 services, 5.1 credit note. | |
| issuer_branch | No | Issuer branch / εγκατάσταση number (BranchID). Default 0 (head office). | |
| counterpart_vat | Yes | Buyer (counterpart) Greek VAT number / ΑΦΜ, 9 digits (EL/GR prefix optional). Always required — v1 covers B2B invoices (invoiceType 1.1/2.1/5.1); retail receipts without a counterpart are not supported yet. | |
| counterpart_branch | No | Buyer branch number. Default 0. | |
| counterpart_country | No | Buyer country ISO code. Default GR. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=false, destructiveHint=false, idempotentHint=false. The description adds significant behavioral context beyond annotations: it transmits to /SendInvoices, returns MARK/UID/QR url, requires authentication headers (x-aade-user-id, x-aade-subscription-key), explains test vs. production mode, and details VAT rate mapping. No contradictions with annotations.
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?
The description is a single paragraph but contains rich information without redundancy. It is front-loaded with the core purpose and then provides details. While it could benefit from better structure (e.g., bullet points for headers, VAT rates), it is concise and every sentence adds value.
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?
Given the complexity (11 parameters, no output schema, nested lines), the description covers key aspects: authentication, mode, VAT mapping, invoice types, counterpart requirement, return values (MARK, UID, QR url). It lacks error handling or pagination details, but for a creation tool, it is fairly complete. The absence of an output schema is partially compensated by mentioning what is returned.
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?
Schema description coverage is 100%, so baseline is 3. The description adds value by explaining that amounts are VAT-exclusive, clarifying VAT rate mapping (e.g., '24 (mainland standard)'), noting default invoice type, and specifying that 'aa' is auto-generated. It also provides context on required headers and mode. This goes beyond the schema's property descriptions.
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?
The description clearly states the tool's purpose: issuing a Greek electronic invoice into the AADE myDATA platform. It uses specific verbs ('issue', 'builds', 'transmits') and identifies the resource ('national AADE myDATA platform'), distinguishing it from the sibling tool 'query_invoice' which is for querying.
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?
The description provides clear context on when to use the tool (issuing invoices to AADE) and mentions that B2B invoices are supported (counterpart_vat required), while retail receipts are not yet supported. It also implicitly contrasts with the sibling tool by focusing on creation. However, it does not explicitly state when not to use it beyond the retail limitation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_invoiceARead-onlyInspect
Look up one of your own transmitted myDATA documents by its MARK. Calls /RequestTransmittedDocs, which returns your transmitted docs with a MARK greater than the value you pass — so this tool requests from MARK-1 and reports whether the exact MARK you asked for was found (found=true means AADE has it registered). Pass mark=0 to list your transmitted documents from the beginning. Safe to call anytime (read-only).
| Name | Required | Description | Default |
|---|---|---|---|
| mark | Yes | Result status values: REGISTERED (found, was transmitted by you), NOT_FOUND (no document with that MARK), LISTED (returned in a range listing). The MARK (unique registration number) returned by create_invoice. Pass 0 to list transmitted docs from the start. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, openWorldHint), the description explains the underlying API behavior: it requests docs with MARK greater than specified value and checks for exact match. This adds useful context about the fetch logic.
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?
Three sentences that are front-loaded with purpose, efficiently explaining the API call, logic, and safety. No wasted words.
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?
Given one parameter, no output schema, and annotations present, the description covers input, mechanism, output indicator (found flag), and implied relationship with sibling tool.
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?
Schema description coverage is 100%, but the schema's description of 'mark' is confusing, mixing result statuses. The main description clarifies that mark is a unique registration number from create_invoice and the behavior of mark=0, adding significant value.
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?
The description clearly states the tool's purpose: lookup of transmitted myDATA documents by MARK. It distinguishes from sibling create_invoice by focusing on querying existing documents.
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?
The description indicates it is for looking up documents and safe to call anytime. While it doesn't explicitly state when not to use, the context and sibling tool (create_invoice) provide clear differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!