mcpField
F
factura-luz

factura-luz

Local
ilopezluna.github.ioFinance2Updated 2w ago
RepositoryVisit website

About factura-luz

factura-luz is a local MCP server for reading and explaining Spanish electricity bills that contain a CNMC QR code. It is intended for people who want an agent to interpret a bill; processing makes no network requests and includes field explanations and a method for assessing contracted power.

Key features

  1. 01Read PDF and image invoices
  2. 02Extract CNMC QR data
  3. 03Explain invoice fields and concepts
  4. 04Provide a contracted-power method resource

Use cases

  1. 01Review contract, consumption, prices, and monthly average
  2. 02Understand bill terminology alongside invoice figures
  3. 03Assess potential savings from lowering contracted power

MCP support

The server exposes `read_invoice`, `explain_concept`, and `list_concepts` tools, plus resources for QR fields, the glossary, contract types, and the power method. It also provides the `entender-factura` prompt.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "ilopezluna-factura-luz": {
      "command": "npx",
      "args": [
        "-y",
        "factura-luz-mcp"
      ]
    }
  }
}
Run commandnpx -y factura-luz-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmfactura-luz-mcp0.1.0

Tools

5

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
qr_urlstringNoAn already-decoded CNMC comparator URL (https://comparador.cnmc.gob.es/comparador/QRE?...). Use this when the QR has been read elsewhere.
invoiceobjectNoThe `invoice` object returned by a previous read_invoice call. Pass this to analyse the same invoice again without re-reading the file, which is much faster.
file_pathstringNoAbsolute path to the invoice file on this machine (PDF, PNG, JPG, WEBP). The file is read locally and never uploaded anywhere.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.