io.github.mehtaphysical13/pdf-tables-mcp — Model Context Protocol (MCP) Server
The io.github.mehtaphysical13/pdf-tables-mcp MCP server provides reliable PDF table extraction. It accepts a URL and returns structured JSON tables. Output includes citations, aligning extracted table data with source locations for traceability during downstream processing.
🛠️ Key Features
- PDF table extraction
- Input via URL
- Structured JSON output for tables
- Included citations with results
🚀 Use Cases
- Convert PDF tables into machine-readable JSON
- Extract tabular data from web-accessible PDFs
- Preserve source traceability via citations during data ingestion
⚡ Developer Benefits
- Programmatic table extraction from a URL
- JSON-formatted results suitable for pipelines
- Citations for verification and auditing
⚠️ Limitations
- Extracts tables from PDFs (not other content types)
- Requires a URL as the entry input