13 个#document-processing MCP 服务器和客户端

QDrant Loader

martin-papy

Enterprise-ready vector database toolkit for building searchable knowledge bases from multiple data sources. Supports multi-project management, automatic ingestion from Confluence/JIRA/Git, intelligent file conversion (PDF/Office/images), and semantic search. Includes MCP server

Suparse

suparse

Extract structured data from PDFs and documents with Suparse AI OCR.

Metis MCP Tools

dagron78

A demo repository for testing the GitHub MCP server

ADP is an Agentic Document Processing (ADP) product independently developed by Laiye. It deeply integrates Vision-Language Model (VLM), Large Language Model (LLM) and agent autonomous decision-making technologies, thoroughly revolutionizing traditional document processing modes.

A powerful Word document processing service based on FastMCP, enabling AI assistants to create, edit, and manage docx files with full formatting support. Preserves original styles when editing content.

FlexOrch MCP

flexorch

FlexOrch MCP converts unstructured documents (PDF, DOCX, invoices, contracts, payroll) into structured, LLM-ready datasets via 6 async tools. Covers the full pipeline: classify → extract fields → mask PII → export JSONL or RAG chunks, with PII detection across 10+ locales (TR, DE

MCP Agentic Workflow Visualization

chrisrafuse

3D visualization of a document processing MCP(Model Contect Protocol) client-server workflow.

Aifais Document Intelligence

AIFAIS

Headless document processing for AI agents. Invoice extraction, contract analysis, and Dutch business verification. Pay-per-use via X402 on Solana. No API keys needed.

Extend

Extend

Turn documents into structured data with Extend: parse (OCR to markdown), extract fields, classify, split multi-document bundles, and fill PDF forms across PDFs, images, Office docs, spreadsheets, and emails.

MCP Server for Veryfi Document Processing

veryfi

Model context protocol server with Veryfi API access

MDMagic MCP Server

MDMagic-MCP

Convert Markdown to DOCX, PDF, and HTML using your own Word templates — your letterhead, your branding, your fonts. Plus 15 designer-built templates for when you don't have your own.

Simulates how 5 real Applicant Tracking Systems (Workday, Greenhouse, Lever, Taleo, iCIMS) parse a CV and surfaces vendor-specific lint warnings. Pure JS lint engine, MIT licensed, no network calls in the lint logic. Vendor rules cite their public sources. Tools exposed: analyze_