Docling MCP MCP
v3.2.0io.github.docling-project/docling-mcp
Convert PDFs and other documents to structured formats via Docling, for AI applications.
transport:stdio
runtime:pypi
Target client
run in your project directory
claude mcp add docling-mcp -e DOCLING_MCP_CONVERSION_MODE=<DOCLING_MCP_CONVERSION_MODE> -e DOCLING_MCP_SERVICE_URL=<DOCLING_MCP_SERVICE_URL> -e DOCLING_MCP_SERVICE_API_KEY=<DOCLING_MCP_SERVICE_API_KEY> -e DOCLING_MCP_SERVICE_TIMEOUT=<DOCLING_MCP_SERVICE_TIMEOUT> -e DOCLING_MCP_SERVICE_MAX_RETRIES=<DOCLING_MCP_SERVICE_MAX_RETRIES> -e DOCLING_MCP_FALLBACK_TO_LOCAL=<DOCLING_MCP_FALLBACK_TO_LOCAL> -e DOCLING_MCP_KEEP_IMAGES=<DOCLING_MCP_KEEP_IMAGES> -e DOCLING_MCP_IMAGES_SCALE=<DOCLING_MCP_IMAGES_SCALE> -e DOCLING_MCP_DO_OCR=<DOCLING_MCP_DO_OCR> -e DOCLING_MCP_DO_TABLE_STRUCTURE=<DOCLING_MCP_DO_TABLE_STRUCTURE> -e DOCLING_MCP_IMAGE_EXPORT_MODE=<DOCLING_MCP_IMAGE_EXPORT_MODE> -- uvx docling-mcp
Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs
This listing does not declare its tools. Connect the server and your client will discover them on the handshake.