Tika MCP Extractor Server

Example Use Cases

• 1

  Extract styled HTML content from PDFs and other document formats.

• 2

  Retrieve detailed metadata and plain text from local files securely.

• 3

  List and manage files available for extraction in a local directory.

Description

The Tika MCP Extractor Server processes files stored locally to extract text, HTML with embedded CSS, and metadata using Apache Tika and PDFBox. It provides four MCP tools and REST endpoints for file listing, content extraction, and metadata retrieval, all without requiring internet access. This makes it ideal for secure, local document processing workflows integrated with MCP-compliant clients.