Skill Detail
Extract structured text, metadata, tables, and images from mixed documents through an MCP server with Kreuzberg
Expose one document-extraction surface to MCP-compatible agents so they can normalize PDFs, Office files, images, HTML, and other mixed inputs before downstream review or indexing.
Data Extraction & TransformationMCP
Data Extraction & Transformation
MCP
Security Reviewed
⭐ 7.6k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill extract-structured-text-metadata-tables-and-images-from-mixed-documents-through-an-mcp-server-with-kreuzberg
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Kreuzberg install or container image, document files to process, MCP-compatible client
Install & setup
Follow the upstream installation guide for the CLI or container, then run Kreuzberg in its documented MCP server mode and attach that server to your MCP-compatible client before sending mixed document inputs for extraction.
Author
kreuzberg-dev
Publisher
Organization
Last updated
Apr 22, 2026
Quick brief
Use Kreuzberg when an agent needs a single MCP-accessible extraction layer for messy document batches before summarization, search, or downstream automation begins. The upstream project explicitly supports MCP server mode and returns structured outputs including text, metadata, tables, images, and code intelligence across many file types. The boundary is document extraction and normalization for agent handoff, not a generic SDK card or broad document platform listing.