5 tagged document parsing, measured the same way as everything else here.
MCP server Claude CodeCodexCursor +2
MCP server "docslicer" as configured in DocSlicer/DocSlicer. Launched with https://github.com/DocSlicer/DocSlicer/releases/download/v0.2.4/docslicer-0.2.4.. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor
A local visual tool for AI models that cannot view images, documents, or other visual material directly. It supports configurable image viewing, text extraction from images, and document parsing.
MCP server Claude CodeCodexCursor +2
MCP wrapper around Apache Tika for document parsing and metadata extraction. Runs locally from the tika-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server for ParseRail — gives Claude, Cursor, and any MCP client native tools to parse documents, extract fields, redact PII, analyze contracts, fight chargebacks, and enrich companies. Runs locally from the @kynth/api-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server "papyrus-engine" as configured in abhichat85/papyrus. Runs locally from the papyrus-engine Python package.