Fintom8 E-Invoicing Agent (MCP)
The official Model Context Protocol (MCP) server for Fintom8.
This server acts as an intelligent bridge to the AI-driven Fintom8 E-Invoice Platform. It enables autonomous agents to validate, audit, and correct e-invoices against the latest European standards (EN16931) and Peppol regulations.
🚀 Features
- PDF to UBL Conversion: Generate compliant e-invoices from any format, including PDF, XML, JSON and CSV.
- Automated Validation: Validate your ZUGFeRD and UBL e-invoices against 300+ EN16931 rules. AI-driven PDF–XML comparison ensures your invoices meet compliance standards.
- Correction: Automatically correct errors in XML files to ensure seamless integration with your system.
🛠️ Installation
The easiest way to use the server is to install it via pip:
pip install e-invoice-mcp
Run the Server
Once installed, you can start the server with:
e-invoice-mcp
🔑 AI Client Configuration
Claude Desktop (Action required)
To use these tools in Claude, add the following to your configuration file:
File: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"fintom8": {
"command": "e-invoice-mcp"
}
}
}
📦 Included Tools
1. convert_pdf_to_invoice
Converts PDF invoices to structured UBL format.
- Args:
pdf_path(path). - Output: UBL XML.
2. validate_invoice (Basic Validation)
Validates UBL/Peppol XML invoices against compliance rules.
- Args:
xml_content(string) orxml_path(path). - Output: Simple JSON report (is_valid, errors).
3. validate_invoice_v2 (Advanced Validation)
Deep validation with optional AI explanations.
- Args:
xml_content(string) orxml_path(path). - Output: Detailed compliance report.
4. correct_invoice_xml
AI-powered correction of invalid XML invoices.
- Args:
xml_content(string) orxml_path(path). - Output: Fixed XML content.
� Privacy & Security
This server acts as a thin client proxy. Data is processed on secure Fintom8 production servers and is not used for AI model training.
License: MIT Website: fintom8.com
1 maintainer
Metadata
1 maintainer
Release files for e-invoice-mcp 0.1.21
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| e_invoice_mcp-0.1.21.tar.gz | 5.3 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| e_invoice_mcp-0.1.21-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 11.3 kB
Release files / e_invoice_mcp-0.1.21.tar.gz
| Download URL | e_invoice_mcp-0.1.21.tar.gz |
|---|---|
| Size | 5.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
43ce6f9b3e7d02710f8ca9e5e1eda0bd5fcd71e15d33fef0f03ae476c23be0ce
|
|
BLAKE2b-256 checksum How to use checksums |
e4a007b35a21192477ae12ed8fcb2af4a4faff3385a1e5fe8eeb923119cc8663
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.10
|
Release files / e_invoice_mcp-0.1.21-py3-none-any.whl
| Download URL | e_invoice_mcp-0.1.21-py3-none-any.whl |
|---|---|
| Size | 6.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
896afb5daf1714dfa851ba2463750c98ff705f16dba12f647a95a70cbbeabfb0
|
|
BLAKE2b-256 checksum How to use checksums |
28b20ed08ab43a723fe3c5049a13291ac81e9d164683b175216457edf2039905
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.10
|
Security for e-invoice-mcp 0.1.21
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
