A straightforward tool for reading PDF files through the Model Context Protocol. It extracts text content from PDFs so Claude can analyze documents directly. The server runs via uvx and communicates over stdio, keeping the setup minimal. You'd reach for this when you need Claude to work with PDF content without manual copy-pasting, whether that's summarizing reports, extracting data, or answering questions about document contents. The implementation uses FastMCP and is licensed under AGPL-3.0, so keep that in mind if you're integrating it into proprietary projects.
claude mcp add --transport stdio atarkowska-fastmcp-pdftools -- uvx fastmcp-pdftools