mcp-docling
If you are the rightful owner of mcp-docling and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
An MCP server that provides document processing capabilities using the Docling library.
The MCP Docling Server is a robust Model Context Protocol server designed to facilitate document processing using the Docling library. It offers a range of tools to convert documents, extract tables, and generate Q&A formats, making it a versatile solution for handling various document types. The server supports both stdio and SSE transport methods, allowing for flexible deployment options. Additionally, it integrates seamlessly with platforms like Llama Stack, enabling enhanced document processing capabilities in LLM applications. The server also includes caching mechanisms to optimize performance for repeated document processing tasks.
Features
- Document conversion to markdown format with optional OCR support.
- Extraction of embedded images and tables from documents.
- Batch processing of multiple documents for efficiency.
- Q&A generation from documents with IBM Watson X integration.
- System information retrieval for configuration and acceleration status.
Tools
convert_document
Convert a document from a URL or local path to markdown format.
convert_document_with_images
Convert a document and extract embedded images.
extract_tables
Extract tables from a document as structured data.
convert_batch
Process multiple documents in batch mode.
qna_from_document
Create a Q&A document from a URL or local path to YAML format.
get_system_info
Get information about system configuration and acceleration status.
