What is verifactu-mcp CLAUDE.md?

Project instructions for a Python server that connects Claude Code and Cursor to VeriFactu, Spain’s electronic invoicing system. They document its design, tools, validation, and HTTP client.

Working on VeriFactu invoice generation, sending, querying, fingerprint chaining, persistence, and tests in this repository.

They give coding agents the project’s fixed decisions and operating rules, reducing incorrect architectural changes or testing assumptions.

How KmOnBeIbI31/verifactu-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to KmOnBeIbI31/verifactu-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/KmOnBeIbI31/verifactu-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/KmOnBeIbI31/verifactu-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kmonbeibi31/verifactu-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/kmonbeibi31/verifactu-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kmonbeibi31/verifactu-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kmonbeibi31/verifactu-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kmonbeibi31/verifactu-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kmonbeibi31/verifactu-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,565 This file is loaded in full into every session.

When invoked 1,565 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01565	$0.01565
Opus 5.5	$0.00626	$0.00626
Sonnet 5.5	$0.00313	$0.00313
Haiku 4.5	$0.00156	$0.00156

Measured 2mo ago against content hash cbd037e584b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verifactu-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

verifactu-mcp — Notas para Claude

Servidor MCP en Python que expone herramientas de facturación electrónica VeriFactu (AEAT) a Claude Code / Cursor. Diseñado para que un usuario pueda generar, encadenar, enviar y consultar registros de facturación desde lenguaje natural sin tocar la documentación técnica de la AEAT.

Decisiones arquitectónicas

Endpoint: REST intermediario https://app.verifactuapi.es/api en VeriFactuClient. No SOAP directo contra AEAT. Esta decisión es explícita; no la propongas revertir salvo que el usuario lo pida.
Layout: src-layout (src/verifactu_mcp/server.py). Todo el código vive en server.py — un único módulo, sin partir por capas hasta que haga falta.
Persistencia de huella: SQLite en ~/.verifactu-mcp/state.db (overrideable con VERIFACTU_STATE_DB). Encadenamiento automático: si huella_anterior no se pasa, se busca la última huella del emisor en DB.
generate_invoice_xml: modo preview — lee la huella anterior pero no persiste. Solo send_invoice persiste, y únicamente tras OK de la API.
Tests aislados: conftest.py redirige VERIFACTU_STATE_DB a tmp_path autouse en cada test. No tocar.

Herramientas (7)

Tool	Función
`generate_invoice_xml`	XML preview, sin enviar
`send_invoice`	POST alta + persiste huella tras éxito
`cancel_invoice`	POST anulación
`check_invoice_status`	GET registro por id
`list_invoices`	GET listado con filtros + paginación
`get_last_hash`	Lee última huella persistida (no toca API)
`calculate_hash`	Hash manual sin lateral effects

Validación

validar_nif(s) cubre DNI (8 dígitos + letra), NIE (XYZ + 7 + letra) y CIF (letra + 7 dígitos + control). Se aplica antes de cualquier llamada a la API a través de _validar_nifs_factura y, para list_invoices / get_last_hash, en el handler directamente.

Cliente HTTP

httpx.Client por llamada (no pool persistente — el server es de baja frecuencia).
Retry exponencial 3 intentos en 5xx y errores de red (ConnectError, TimeoutException, ReadError). Base 0.5 s, backoff 2^n.
4xx no reintenta — propaga inmediato.
Categorización del handler: http_error / network / config / unexpected.

Read the full file on GitHub · 74 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 74 lines · 1,565 tokens per session scan A cbd037e584b4

Subscribe to this mod's changes

verifactu-mcp CLAUDE.md is an instructions file published in the GitHub repository KmOnBeIbI31/verifactu-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,565 tokens to every session, about $0.0063 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Finance and fintech Legal and compliance

verifactu-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
verifactu-mcp CLAUDE.mdKmOnBeIbI31/verifactu-mcp	Instructions file	0	5mo ago	MIT	A	1,565	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

verifactu-mcp: Instructions file for Claude Code