Kreuzberg MCP Server

Content

Kreuzberg MCP Server exposes Kreuzberg's document intelligence engine through the Model Context Protocol. It lets Claude, Cursor, and custom MCP clients extract content from files, generate embeddings, chunk text, manage cache state, detect formats, and inspect supported extraction capabilities without writing custom extraction code.

The upstream MCP guide documents stdio mode with kreuzberg mcp as the default local setup. Docker can also run the same MCP mode when file access and cache volumes need to be controlled more explicitly.

Source Review

• https://github.com/kreuzberg-dev/kreuzberg
• https://github.com/kreuzberg-dev/kreuzberg/blob/main/README.md
• https://docs.kreuzberg.dev/guides/mcp-integration/
• https://docs.kreuzberg.dev/cli/usage/
• https://docs.kreuzberg.dev/guides/docker/
• https://github.com/kreuzberg-dev/kreuzberg/pkgs/container/kreuzberg
• https://pypi.org/pypi/kreuzberg/json

These sources were reviewed on 2026-06-06. Prefer the live MCP integration guide, CLI usage docs, Docker guide, repository README, container package, and PyPI metadata for current install commands, server modes, feature flags, and runtime dependencies.

Features

• Run an MCP server over stdio with kreuzberg mcp.
• Extract file content and metadata from PDFs, Office documents, images, HTML, XML, email, archives, academic formats, text files, and code.
• Detect MIME types and list supported formats.
• Batch-extract several files.
• Generate embeddings and chunk text when configured.
• Extract structured data when the required LLM feature is available.
• Inspect and clear cache state.
• Use config files to apply extraction defaults.
• Run the MCP server through Docker with controlled file and cache mounts.

Installation

Install Kreuzberg with its optional feature bundle:

pip install "kreuzberg[all]"

Start the stdio MCP server:

kreuzberg mcp

Configure an MCP client with the documented command:

{
  "mcpServers": {
    "kreuzberg": {
      "command": "kreuzberg",
      "args": ["mcp"]
    }
  }
}

For containerized setups, mount only the document directories and config files the agent should access.

Use Cases

• Extract text and metadata from PDFs, Office files, images, and email for analysis in Claude.
• OCR scanned documents or screenshots before summarization.
• Chunk long documents for RAG and agent workflows.
• Generate embeddings for document-derived text when configured.
• Detect file types before choosing an extraction path.
• Build a local document-processing MCP workflow without exposing documents to a hosted extraction service.

Safety and Privacy

Kreuzberg can turn private files into model-visible text. That is useful, but it also means access boundaries matter. Mount or expose only approved directories, avoid broad workspace paths, and start with a small file before batch processing.

Review OCR, embedding, VLM, and LLM provider configuration before enabling features that can send document-derived content outside the local machine. Keep cache directories, logs, and extracted outputs out of shared repos unless they are approved for publication.

Duplicate Check

No kreuzberg-dev/kreuzberg entry, Kreuzberg MCP entry, or matching Kreuzberg source URL was found in content/mcp.