mcpField
P
Paperless MCP - Document Management System

Paperless MCP - Document Management System

Local
github.com/PDangelmaierFiles & Storage2Updated 82w ago

About Paperless MCP - Document Management System

Paperless MCP is an open-source document management system for organizations handling digital records. It combines storage and search with OCR, classification, metadata extraction, access controls, and document workflows.

Key features

  1. 01Document storage and folder organization
  2. 02Metadata, tags, and advanced search
  3. 03OCR and metadata extraction
  4. 04Automated document classification
  5. 05Access controls and audit logs
  6. 06REST API and customizable workflows

Use cases

  1. 01Digitizing and organizing scanned records
  2. 02Finding documents by text and metadata
  3. 03Classifying incoming documents automatically

MCP support

The README describes a document management system and REST API, but does not specify MCP tools or resources exposed to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"Paperless-MCP-Server": {
"command": "npx",
"args": [
"-y",
"paperless-mcp"
]
}
}
}
Run commandnpx -y paperless-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmpaperless-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Paperless MCP - Document Management System

Paperless MCP Logo

A modern, efficient document management system for the digital workplace

Features • Installation • Usage • API • Configuration • Contributing • License

Overview

Paperless MCP is an open-source document management system designed to streamline the handling of digital documents in enterprise environments. It provides a comprehensive solution for storing, organizing, searching, and processing documents, eliminating the need for physical paperwork and simplifying document workflows.

The system offers robust document processing capabilities, including OCR (Optical Character Recognition), metadata extraction, and automated document classification, all while maintaining strict security and access controls.

Features

Document Storage & Organization

  • Secure cloud or on-premises document storage
  • Hierarchical folder structure
  • Custom metadata and tagging
  • Advanced search capabilities

Document Processing

  • OCR for scanned documents
  • Automated document classification
  • Metadata extraction
  • PDF processing and manipulation

Security & Compliance

  • Role-based access control
  • Audit logging for all document activities
  • Encryption of sensitive data
  • Compliance with industry standards (GDPR, HIPAA, etc.)

Integration & Extensibility

  • RESTful API for third-party integration
  • Webhook support for automation
  • Customizable workflow engine
  • Plugin architecture for extending functionality

User Experience

  • Intuitive web-based user interface
  • Mobile-responsive design
  • Document preview and annotation
  • Batch operations for efficient document handling

Installation

Prerequisites
  • Node.js (v16 or later)
  • npm or yarn
  • PostgreSQL (v13 or later)
  • Docker (optional, for containerized deployment)
Local Installation
  1. Clone the repository:
git clone https://github.com/yourusername/paperless-mcp.git
cd paperless-mcp
  1. Install dependencies:
npm install
  1. Set up environment variables:
cp .env.example .env
# Edit .env with your configuration
  1. Run database migrations:
npm run migrate
  1. Start the development server:
npm run dev
Docker Installation
  1. Clone the repository:
git clone https://github.com/yourusername/paperless-mcp.git
cd paperless-mcp
  1. Build and start the Docker containers:
docker-compose up -d

The application will be available at http://localhost:3000.

Usage

Basic Operations
Document Upload
import { DocumentService } from 'paperless-mcp';

const documentService = new DocumentService();
const result = await documentService.uploadDocument({
file: fileBuffer,
metadata: {
    title: 'Invoice #12345',
    category: 'Finance',
    tags: ['invoice', '2023', 'vendor-abc']
}
});
Document Retrieval
const document = await documentService.getDocument(documentId);
Document Search
const searchResults = await documentService.searchDocuments({
query: 'invoice',
filters: {
    category: 'Finance',
    dateRange: {
    from: '2023-01-01',
    to: '2023-12-31'
    }
},
page: 1,
limit: 20
});
CLI Usage

Paperless MCP also provides a command-line interface for administrative tasks:

# Display help
npx paperless-mcp --help

# Initialize the system
npx paperless-mcp init

# Import documents from a directory
npx paperless-mcp import --source /path/to/documents

# Run system diagnostics
npx paperless-mcp diagnose

API Documentation

Paperless MCP exposes a RESTful API for integration with other systems. The API is available at /api/v1 and requires authentication via API keys or JWT tokens.

Authentication
POST /api/v1/auth/login

Request body:

{
"username": "admin",
"password": "your-password"
}

Response:

{
"token": "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...",
"expiresAt": "2023-12-31T23:59:59Z"
}
Documents API
Create Document
POST /api/v1/documents

Request body:

{
"title": "Invoice #12345",
"content": "Base64 encoded file content...",
"metadata": {
    "category": "Finance",
    "tags": ["invoice", "2023"]
}
}
Get Document
GET /api/v1/documents/:id
Search Documents
GET /api/v1/documents/search?q=invoice&category=Finance&from=2023-01-01&to=2023-12-31&page=1&limit=20

For a complete API reference, see the API Documentation.

Configuration

Paperless MCP can be configured through environment variables, configuration files, or the smithery.yaml file.

Environment Variables
  • PORT: The port the server will listen on (default: 3000)
  • DATABASE_URL: PostgreSQL connection string
  • STORAGE_TYPE: Storage backend ('local', 's3', 'azure', etc.)
  • STORAGE_PATH: Local storage path (if STORAGE_TYPE=local)
  • LOG_LEVEL: Logging level ('debug', 'info', 'warn', 'error')
  • JWT_SECRET: Secret for JWT token generation
  • OCR_ENGINE: OCR engine to use ('tesseract', 'azure', etc.)
Configuration File

For more advanced configuration, create a config.js or config.json file in the project root. Example:

{
"server": {
    "port": 3000,
    "host": "0.0.0.0",
    "cors": {
    "enabled": true,
    "origins": ["https://example.com"]
    }
},
"database": {
    "url": "postgresql://user:password@localhost:5432/paperless",
    "pool": {
    "min": 2,
    "max": 10
    }
},
"storage": {
    "type": "s3",
    "config": {
    "bucket": "paperless-documents",
    "region": "us-west-2"
    }
}
}

Contributing

We welcome contributions to Paperless MCP! Please feel free to submit issues, feature requests, and pull requests.

Development Setup
  1. Fork the repository
  2. Clone your fork: git clone https://github.com/yourusername/paperless-mcp.git
  3. Create a feature branch: git checkout -b feature/my-feature
  4. Make your changes
  5. Run tests: npm test
  6. Commit your changes: git commit -m 'Add my feature'
  7. Push to the branch: git push origin feature/my-feature
  8. Submit a pull request
Coding Standards
  • We follow the TypeScript Coding Guidelines
  • All code should be properly typed
  • Unit tests are required for new features
  • Documentation should be updated with any changes
Documentation
  • API documentation is generated using TypeDoc
  • Update the README.md if you add or change features
  • Add examples for new functionality

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

  • Thanks to all contributors who have helped shape this project
  • Special thanks to the open-source community for the tools and libraries that make this project possible

Made with ❤️ by the Paperless MCP Team

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.