MCP'S
kreuzberg
by kreuzberg-dev
Overview
Kreuzberg is a document intelligence framework with a Rust core, native bindings, and an MCP server for extracting text from documents.
Details
Kreuzberg describes itself as document intelligence with a Rust core and native bindings. The GitHub source says it can extract text, metadata, images, and structured information from PDFs, Office documents, images, and 97+ formats. It is available for Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, R, C, and TypeScript environments including Node, Bun, Wasm, and Deno, and can also be used through a CLI, REST API, Docker image, or MCP server. Its MCP Server documentation says it enables AI tools such as Claude Desktop and Cursor to extract text from documents through the Model Context Protocol.
When to Use
Use when an AI tool or agent needs document text extraction through a Model Context Protocol server. Use when you need a document intelligence framework that can be accessed as an SDK, CLI, REST API, Docker image, or MCP server. Use when working across many document formats including PDFs, Office documents, images, and other supported formats.
Getting Started
- Review the project repository at https://github.com/kreuzberg-dev/kreuzberg.
- Read the Kreuzberg documentation at https://docs.kreuzberg.dev/.
- For MCP usage, follow the MCP Server guide at https://kreuzberg.dev/user-guide/mcp-server/.
- Run a small extraction trial against representative documents before relying on it in production.
Key Features
- •Rust core with native bindings.
- •Extracts text, metadata, images, and structured information from documents.
- •Supports PDFs, Office documents, images, and 97+ formats.
- •Usable as an SDK, CLI, REST API, Docker image, or MCP server.
- •MCP server support for AI tools such as Claude Desktop and Cursor.
Capabilities
- •document-text-extraction
- •metadata-extraction
- •image-extraction
- •structured-information-extraction
- •mcp-server
- •cli
- •rest-api
- •sdk
Last updated Jun 1, 2026