</>MCP Agents Market
Plugin

xberg

by xberg-io9.2kRustUpdated 2026-08-25

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured data from 101 formats (115 file extensions) plus code intelligence for 371 code languages. 15 language bindings — Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript — plus CLI, REST API

Claude CodeCodexCursorGitHub Copilot CLI

Xberg is a polyglot document intelligence plugin for Claude Code and other AI coding assistants that extracts text, metadata, images, tables, and structured data from 101 file formats (115 extensions) plus code intelligence for 371 programming languages. Built on a high-performance Rust core, it provides native bindings for 15 languages including Python, TypeScript, Java, Go, Ruby, PHP, and Elixir, and can be deployed as a library, CLI tool, REST API, or MCP server. The plugin enables AI assistants to process PDFs, Office documents, spreadsheets, images (with OCR), audio/video transcription, web pages, archives, and source code with syntax-aware chunking, embeddings, and structured LLM extraction.

Key Features

Supports 101 document formats across 115 file extensions: PDFs, Office files, images, HTML, email, eBooks, scientific publications, and structured data
Code intelligence for 371 programming languages via tree-sitter: extracts functions, classes, imports, symbols, and docstrings with syntax-aware chunking for RAG
OCR with multiple backends (Tesseract, PaddleOCR, Candle, VLM) including fallback chains and confidence scoring
Audio and video transcription via Whisper ONNX (MP3, M4A, WAV, WebM, MP4 tracks)
Recursive archive extraction with zip-bomb protection for .zip, .tar, .gz, .7z formats
Native bindings for 15 languages (Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript, Dart, Swift, Kotlin, Zig, WASM, C FFI)
Embeddings with local ONNX models or 165 provider-hosted options via liter-llm, plus cross-encoder reranking
Structured LLM extraction with schema-driven JSON output from local (Ollama, LM Studio, vLLM) or remote providers

Use Cases

  • 01Extract structured data from PDF invoices, contracts, and forms for automated document processing pipelines
  • 02Build RAG systems over codebases by extracting semantic chunks from 371 programming languages with function and class boundaries
  • 03Process scanned documents and images with OCR to extract text and tables from receipts, business cards, and handwritten notes
  • 04Transcribe meeting recordings and video content to searchable text with Whisper speech-to-text models
  • 05Crawl and extract content from websites with automatic link following and HTML-to-Markdown conversion
  • 06Generate embeddings for document search and similarity matching using local or cloud-based models

Related Plugins

View more

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Plugin216.1k

claude-mem

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

Plugin95k

Understand-Anything

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Plugin84.9k

rtk

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Plugin82.1k

xberg — FAQ

What is the Xberg Claude Code plugin?+

Xberg is a document intelligence plugin that gives Claude Code the ability to extract text, tables, metadata, and structured data from over 100 file formats including PDFs, Office documents, images with OCR, audio transcription, and code from 371 programming languages. It provides extraction APIs, OCR backends, and configuration options directly within your AI coding assistant.

How do I install the Xberg plugin in Claude Code?+

Run '/plugin marketplace add xberg-io/xberg' in Claude Code to add the repository, then run '/plugin install xberg@xberg' to install the plugin. The plugin is immediately available for use after installation.

Which AI coding assistants support the Xberg plugin?+

Xberg works with Claude Code, Codex CLI, Cursor, Gemini CLI, Factory Droid, GitHub Copilot CLI, and opencode. Each assistant has its own installation command documented in the README.

Does Xberg require API keys or external services?+

The core extraction functionality works completely offline with no API keys required. Optional features like provider-hosted embeddings (OpenAI, Anthropic, etc.), cloud-based OCR via VLM, and remote LLM structured extraction require respective API keys when enabled.

Is Xberg free and open source?+

Yes, Xberg is released under the MIT License and is fully open source. The core library, all language bindings, CLI, REST API, and MCP server implementations are free to use.

Can I use Xberg as a standalone library or only as a plugin?+

Xberg can be used as a native library in 15 programming languages, as a CLI tool with 12 commands, as a REST API server, or as an MCP server for Claude Desktop and other clients. The Claude Code plugin is just one deployment mode among many.

How do I install xberg?+

Open the source repository on GitHub and follow its README. xberg is a plugin — MCP Agents Market links you directly to the official repo.

Is xberg free?+

xberg is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.

Related searches

Developer Tools PluginsData Science & ML PluginsDocumentation PluginsBest MCP ServersBest SkillsBest AgentsTop rated listingsClaude Code toolsBrowse all categories