Claix

This endpoint accepts a tabular file (.xlsxor.csv) and returns it transformed into JSON with the exact structure you define via a schema. The file columns do not need to match schema property names literally: the system automatically recognizes synonyms, abbreviations, translations, and variants.

It is intended forserver-to-serverintegrations (backends, scripts, n8n/Zapier/Make). It must not be called from an end user's browser because it requires a secret API key.

Every request must include your API key. It is a personal server credential, distinct from any session token, and should be handled with the same care as a database password.

Option A — Dedicated header (recommended):

Option B — Standard Authorization header:

Authorization: Bearer <YOUR_API_KEY>

Either one is sufficient. If you send both,x-api-keytakes priority.

Before processing the file, the system validates that:

- The API key exists and is active.
- The associated account is active (not suspended).

If validation fails, the request is rejected with401without processing the file.

Method:POST ·Content-Type:multipart/form-data

Field names must be exactlyfileandschema_id. The schema must be of the Excel → JSON type; if you send one of the opposite type, you will receive400.

- Formats:.xlsx,.csv.
- At least one header row and one data row.
- If there are multiple sheets, only the first is processed.
- Have your API key and the correct schema_id ready.
- Build a POST request to the endpoint URL.
- Add the authentication header.
- Sendmultipart/form-datawithfileandschema_id.
- Check the HTTP status code: only 200 indicates success.

See the panel on the right for examples in cURL, JavaScript, Node.js, Python, PHP, and n8n. You can switch languages with the selector at the top and copy the code directly.

{ "success": true, "schema_utilizado": "Leads de Ventas", "total_filas_procesadas": 247, "mapa_columnas": { "Nom_cliente": "nombre_completo", "Tlf": "telefono_movil", "mail de contacto": "email_contacto" }, "data": [ { "nombre_completo": "Ana María Gómez", "cargo": "CEO & Founder", "empresa": "TechSolutions", "email_contacto": "ana.gomez@techsolutions.com", "telefono_movil": "+1 (555) 019-2231" } ] }

{ "error": "Descripción legible del problema.", "detalle": "Información técnica adicional (solo presente en algunos casos)." }

400— Invalid request: missing file or schema_id, incorrect multipart, corrupt file, no data rows, or schema of the wrong type.

401— Authentication failed: key missing, nonexistent, deactivated, or account suspended.

404— schema_id does not exist or does not belong to your account.

422— File read but no matches with the schema.

502— AI service failure (transient; retry with backoff).

405— Method other than POST. ·500— Internal error.

- Validate the HTTP status code before reading data.
- Only columns with a real match in the schema appear.
- Retry automatically only on 500 and 502, never on 4xx unless the request changes.
- Savemapa_columnasfor traceability during testing.
- Do not include your API key in frontend code or public repositories.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

An MCP server that provides tools for downloading, compressing, optimizing images, and extracting text via OCR. Built using the Model Context Protocol (MCP), this server enables AI assistants to download images from URLs or search, compress and convert images with various format options, batch process entire directories with auto-generated reports, synchronize filename references across your project, and extract printed text from images.

A local MCP server implementing Retrieval-Augmented Generation (RAG) with sentence window retrieval and support for multiple file types.

Parses PDF files from a URL into structured formats like JSON and Markdown.

Agentic Document Parsing and Extraction (ADP)

ADP automatically classifies overseas invoices, domestic vouchers, procurement contracts, logistics documents, financial statements and trading contracts, and accurately extracts key fields. It also supports table parsing, content verification and multilingual recognition. Requiring no template setup, data labeling or ongoing rule maintenance, it efficiently handles high-volume document processing tasks.

Analyze and extract information from DLIS (Digital Log Interchange Standard) files, including channel data and metadata.

Read, analyze, and manipulate data in Excel (XLSX, XLS) and CSV files with advanced filtering and analytics.

Convert various file formats for documents and images, such as DOCX, PDF, CSV, and more.

Recognize and extract text from handwritten documents using the Handwriting OCR service.

Turn PDF bank statements into checked Excel, CSV or JSON with balance validation.

An MCP server for Optical Character Recognition (OCR) using the Tesseract engine.