Italy Invoices (FatturaPA / SdI via Invoicetronic)
Server Details
Italy FatturaPA invoices for AI agents: build FPR12 XML, transmit to the SdI, query status.
- Status
- Healthy
- 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 4.4/5 across 2 of 2 tools scored.
The two tools have clearly distinct purposes: one creates/sends an invoice, the other queries its processing status. No overlap or ambiguity.
Both tools follow a consistent verb_noun pattern (create_invoice, query_invoice), making the action and resource clear.
Only 2 tools for a domain that typically includes listing, canceling/credit notes, and managing recipients. Feels too minimal for a full invoicing server.
Covers only create and query status. Missing crucial operations like listing invoices, issuing credit notes (mentioned but no tool), or updating drafts. Significant gaps.
Available Tools
2 toolscreate_invoiceAInspect
Issue an Italy B2B electronic invoice (fattura elettronica) in FatturaPA format (FPR12) and transmit it to the national SdI (Sistema di Interscambio) via Invoicetronic. Builds the FatturaPA XML (seller/buyer P.IVA + optional Codice Fiscale, address, line items, IVA breakdown) and uploads it under your own Invoicetronic API key. Bring your own credential as header x-invoicetronic-key — ik_test_ keys are free sandbox (no fiscal effect), ik_live_ keys transmit real invoices to the SdI (same base URL; the key prefix selects the environment). Italian IVA rates supported: 22 (ordinaria), 10, 5, 4 (ridotte). Amounts are in EUR. Transmission is asynchronous: this returns a send id — poll query_invoice with it to learn the SdI outcome (SENT / DELIVERED / REJECTED / NOT_DELIVERED). There is no cancel at the SdI level: to reverse an invoice you issue a credit note (nota di credito) as a new invoice.
| Name | Required | Description | Default |
|---|---|---|---|
| lines | Yes | Invoice line items. Each: description, unit_price (net, IVA-exclusive, EUR), vat_rate (22|10|5|4), optional quantity (default 1). | |
| currency | No | Document currency (Divisa). Default EUR. | |
| issue_date | No | Invoice date (Data), YYYY-MM-DD. Default: today (UTC). | |
| seller_cap | Yes | Seller postal code / CAP, 5 digits. | |
| seller_vat | Yes | Seller Partita IVA (P.IVA), 11 digits, e.g. 12345678903. IT prefix optional. | |
| seller_city | Yes | Seller city / Comune. | |
| seller_name | Yes | Seller legal name / denominazione (CedentePrestatore). | |
| customer_cap | Yes | Buyer postal code / CAP, 5 digits. | |
| customer_vat | No | Buyer Partita IVA (P.IVA), 11 digits. Provide this and/or customer_tax_code. | |
| customer_city | Yes | Buyer city / Comune. | |
| customer_name | Yes | Buyer legal name / denominazione (CessionarioCommittente). | |
| document_type | No | FatturaPA TipoDocumento. Default TD01 (fattura). Use TD04 for a credit note (nota di credito). | |
| seller_regime | No | Seller tax regime code (RegimeFiscale). Default RF01 (ordinario). Others: RF19 (forfettario), etc. | |
| invoice_number | No | Invoice number (Numero). Auto-generated if omitted. | |
| seller_address | Yes | Seller street address (Sede/Indirizzo). | |
| seller_province | No | Optional seller province, 2-letter code (e.g. MI, RM). | |
| seller_tax_code | No | Optional seller Codice Fiscale (11 digits for companies or 16 chars for individuals). | |
| customer_address | Yes | Buyer street address (Sede/Indirizzo). | |
| customer_country | No | Buyer country code (Nazione). Default IT. | |
| pec_destinatario | No | Optional recipient PEC email — used when codice_destinatario is 0000000 to route the invoice by certified email. | |
| customer_province | No | Optional buyer province, 2-letter code. | |
| customer_tax_code | No | Buyer Codice Fiscale (16 chars for individuals, 11 digits for companies). Provide this and/or customer_vat. | |
| codice_destinatario | No | Recipient SdI Codice Destinatario, 7 chars. Default 0000000 (recipient retrieves from the tax drawer / cassetto fiscale, or set pec_destinatario). |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral context beyond annotations: asynchronous transmission, return of a send id, need to poll with query_invoice, no cancel at SdI level, and sandbox vs live behavior via key prefix. No contradiction 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 longer but well-structured: starts with the main action, then technical details, environment key, rates, async behavior, and cancellation. Every sentence adds necessary information; no fluff.
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 complex tool with 23 parameters and no output schema, the description covers authentication, environment selection, async polling, and cancellation. It lacks explicit return value structure but mentions the send id and references query_invoice for status.
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 coverage is 100%, but the description adds value by explaining the FatturaPA format, IVA rates, EUR currency, and parameter groups (seller/buyer info, line items). It also explains the document_type for credit notes, which adds meaning beyond schema.
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 it issues an Italy B2B electronic invoice in FatturaPA format and transmits it to SdI. It distinguishes from the sibling tool query_invoice by focusing on creation and transmission, using specific terms like 'fattura elettronica' and 'FPR12'.
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 explicit guidance on when to use the tool (issuing Italian invoices), authentication via API key header, sandbox vs live environment, and the process for reversal via credit note. It does not explicitly state when not to use it, but the context of Italy B2B is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query_invoiceARead-onlyInspect
Check the SdI processing status of an invoice sent by create_invoice, using its send id. FatturaPA transmission is asynchronous. Status values: SENT (Inviato — accepted by the SdI, not yet delivered to the recipient; poll again shortly); DELIVERED (Consegnato — delivered to the recipient, the invoice is fiscally complete); REJECTED (Scartato — the SdI rejected it for a validation error; fix the data and create_invoice again); NOT_DELIVERED (ImpossibilitaDiRecapito / MancataConsegna — the invoice is legally valid and available in the recipient's tax drawer, but could not be pushed to their receiving system); PROCESSING (no SdI notification yet — poll again shortly). Safe to call anytime.
| Name | Required | Description | Default |
|---|---|---|---|
| send_id | Yes | The send id returned by create_invoice. |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint and openWorldHint. The description adds context about asynchronous transmission, polling behavior, and safety, enhancing transparency beyond 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?
Purpose is front-loaded, sentences are informative but could be slightly more concise. However, the structure is clear and easy to parse.
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 a single parameter, no output schema, and good annotations, the description is very complete: it explains async behavior, all status values, and safety, leaving no gaps for an agent.
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% with send_id described. The description mentions the send id but does not add substantial meaning beyond the schema definition. Baseline score appropriate.
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 verb 'check', the resource 'SdI processing status', and specifies it is for invoices sent by create_invoice, distinguishing it from the sibling tool.
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?
Explicitly states when to use (after create_invoice, for polling) and provides status meanings. Lacks explicit when-not-to-use but alternatives are limited to create_invoice which serves a different purpose.
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!