xberg

xberg

Multilingual document intelligence framework that extracts text, metadata, and structured information from various formats.

MCPDataOpen source
Type
MCP
Transport
http
Open source
Yes
GitHub Stars
★ 8.6k
Source
mcp-github

Overview

Xberg is a document intelligence framework built on a Rust core, capable of extracting text, metadata, images, and structured information from over 97 file formats including PDFs, Office documents, and images. It offers native bindings for 16 programming languages and can run via CLI, REST API, or MCP server. Ideal for AI and RAG pipelines requiring fast and reliable document content extraction.

Capabilities

  • Extract text from 97+ file formats
  • Extract metadata and structured information
  • Support code intelligence for 306 programming languages
  • Built-in OCR and audio transcription capabilities

Use cases

Document processing and analysisCode intelligence extractionOCR and audio transcriptionData preprocessing for AI and RAG pipelines

Setup

Requires: API KeyNode 环境
Install via npm: `npm install @xberg/node` or use the Docker image: `docker pull ghcr.io/xberg-io/xberg`

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

What file formats does Xberg support?

Supports over 97 formats, including PDFs, Office documents, images, and more.

How do I use Xberg's OCR functionality?

Built-in OCR engines like Tesseract are available—simply call the relevant methods directly.

Related skills